Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13807
    Prev
    Next
    INDEX
    Explanations

    programming code structures and syntax, particularly related to conditional statements and function declarations

    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
    430
    +0.16
    0.5%
    8
    +0.15
    0.5%
    38
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.16
    0.03
    485
    +0.15
    0.02
    656
    +0.12
    0.02
    Negative Logits
    natureconservancy
    -1.28
    kefeller
    -0.98
    tnc
    -0.91
    ASED
    -0.91
     GOODMAN
    -0.90
    NVIDIA
    -0.89
    chnology
    -0.88
     fundament
    -0.87
    eness
    -0.87
    #$
    -0.86
    POSITIVE LOGITS
    words
    1.10
    pid
    1.07
    riot
    0.97
     Shutdown
    0.91
    IRE
    0.89
     listen
    0.85
     Listen
    0.85
    ihad
    0.84
    if
    0.83
    ftime
    0.82
    Activations Density 0.152%

    No Known Activations