© 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 EvalsExportsAPI 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. 33596
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or actions, possibly in a negative context such as mistakes or frustrations

    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
    393
    +0.11
    0.7%
    718
    +0.08
    0.5%
    445
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.25
    484
    +0.08
    0.15
    0
    +0.08
    0.15
    Negative Logits
    wake
    -0.48
    nostic
    -0.47
    urden
    -0.46
    olphins
    -0.45
    card
    -0.45
    anza
    -0.44
    sson
    -0.44
    rain
    -0.43
    iaz
    -0.43
     Crane
    -0.43
    POSITIVE LOGITS
    rogen
    0.63
    rogens
    0.63
     then
    0.57
     forth
    0.55
    romeda
    0.54
     consequently
    0.52
    alus
    0.52
     heals
    0.51
     parcel
    0.49
     THEN
    0.48
    Activations Density 7.856%

    No Known Activations