© 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. 7687
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities, investigations, and requests for help

    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
    631
    +0.14
    0.6%
    122
    +0.12
    0.5%
    676
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.14
    0.07
    51
    +0.12
    0.06
    417
    +0.10
    0.04
    Negative Logits
    eatures
    -0.81
    ophon
    -0.79
    ategory
    -0.78
    bey
    -0.77
    ntil
    -0.75
    emale
    -0.72
    aval
    -0.72
    imaru
    -0.68
     neighb
    -0.68
    total
    -0.67
    POSITIVE LOGITS
     counselor
    0.76
     decipher
    0.74
     Psychic
    0.72
    tips
    0.72
     recharge
    0.70
     è£ıç
    0.70
    Streamer
    0.68
     supplies
    0.68
     trolling
    0.67
    hooting
    0.67
    Activations Density 0.765%

    No Known Activations