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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4063
    Prev
    Next
    INDEX
    Explanations

    references to carrying objects or weapons with oneself

    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
    393
    +0.18
    0.6%
    102
    +0.16
    0.6%
    526
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.08
    526
    +0.16
    0.01
    761
    +0.15
    0.06
    Negative Logits
    oulos
    -0.93
    ophon
    -0.93
    ouf
    -0.91
    baugh
    -0.91
    æ©Ł
    -0.89
    xtap
    -0.89
    esley
    -0.86
    bush
    -0.85
    ilight
    -0.85
    iseum
    -0.85
    POSITIVE LOGITS
    stood
    1.28
     regards
    1.27
     regard
    1.18
     luggage
    0.98
    own
    0.96
     baggage
    0.94
     transporting
    0.91
    standing
    0.89
     impunity
    0.86
     utmost
    0.86
    Activations Density 1.016%

    No Known Activations