© 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. 35715
    Prev
    Next
    INDEX
    Explanations

    mentions of significant changes or transitions

    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
    447
    +0.26
    1.1%
    288
    +0.16
    0.7%
    195
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.26
    0.04
    448
    +0.16
    0.04
    402
    +0.14
    0.06
    Negative Logits
     Seym
    -0.75
    amina
    -0.75
    Interstitial
    -0.74
    gom
    -0.74
    ORED
    -0.71
     jug
    -0.69
    CRIP
    -0.69
    DOC
    -0.68
    gdala
    -0.68
    tics
    -0.66
    POSITIVE LOGITS
     shift
    0.99
     gears
    0.98
     shifts
    0.93
     shifting
    0.85
     shif
    0.84
    rers
    0.83
    otom
    0.82
     sands
    0.82
    over
    0.81
     toward
    0.81
    Activations Density 7.957%

    No Known Activations