© 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. 8562
    Prev
    Next
    INDEX
    Explanations

    mentions of specific technological devices and models

    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
    436
    +0.16
    0.6%
    690
    +0.11
    0.5%
    636
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    639
    +0.16
    0.09
    284
    +0.11
    0.08
    398
    +0.11
    0.06
    Negative Logits
     ancest
    -0.83
    Ô
    -0.81
     timeless
    -0.80
    £ı
    -0.80
    jriwal
    -0.80
     feder
    -0.76
     reckoning
    -0.71
     mortg
    -0.68
     perspective
    -0.68
     fray
    -0.67
    POSITIVE LOGITS
    ooth
    1.16
    vous
    0.93
    shit
    0.79
    ingo
    0.75
    estern
    0.72
    monary
    0.71
    lah
    0.71
     Panda
    0.71
    rics
    0.71
    Parts
    0.69
    Activations Density 2.852%

    No Known Activations