© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 31959
    Prev
    Next
    INDEX
    Explanations

    requests for submission or sharing of content, such as nominations, submissions, and sharing tips

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    604
    +0.07
    0.5%
    592
    +0.07
    0.5%
    276
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.07
    0.05
    184
    +0.07
    0.05
    604
    +0.07
    0.06
    Negative Logits
    ppard
    -0.53
    runs
    -0.48
    akening
    -0.47
    peror
    -0.47
    ãĤ°
    -0.45
    culus
    -0.45
    Real
    -0.44
    ords
    -0.43
    ashington
    -0.43
    ablished
    -0.42
    POSITIVE LOGITS
     yourselves
    0.82
     yourself
    0.79
     Yourself
    0.64
     your
    0.57
    owship
    0.54
     submissions
    0.54
    ãĥĥãĥī
    0.52
     Submit
    0.52
     attribution
    0.51
     receipts
    0.51
    Activations Density 9.493%

    No Known Activations