© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7387
    Prev
    Next
    INDEX
    Explanations

    additionally explanations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    515
    +0.13
    0.5%
    62
    +0.11
    0.4%
    484
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.13
    0.07
    537
    +0.11
    0.08
    41
    +0.10
    0.07
    Negative Logits
    nam
    -0.90
    untu
    -0.84
    onom
    -0.81
    amental
    -0.79
    raised
    -0.78
    alien
    -0.78
    pter
    -0.76
    rum
    -0.76
    AppData
    -0.76
    endi
    -0.74
    POSITIVE LOGITS
    Route
    1.50
     routes
    1.48
     Route
    1.46
    route
    1.38
     route
    1.34
     highways
    1.33
     commute
    1.23
     Rout
    1.22
     Interstate
    1.21
     Highway
    1.21
    Activations Density 3.934%

    No Known Activations