© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 172
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    285
    +0.20
    0.8%
    679
    +0.17
    0.6%
    399
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.20
    0.09
    391
    +0.17
    0.06
    107
    +0.13
    0.06
    Negative Logits
    apan
    -0.89
     hob
    -0.88
     clin
    -0.81
     docks
    -0.79
     herbal
    -0.79
    kee
    -0.79
     dex
    -0.79
     helicop
    -0.78
    opath
    -0.77
     jelly
    -0.77
    POSITIVE LOGITS
    ����
    1.16
     Surely
    1.13
    .?
    1.10
     Certainly
    1.08
     Wouldn
    1.07
     Answer
    1.06
     Nope
    1.06
     Presumably
    1.05
    Answer
    1.04
     Sure
    1.03
    Activations Density 0.257%

    No Known Activations