© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13395
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving and brainstorming

    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
    +0.19
    0.7%
    235
    +0.14
    0.5%
    612
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.19
    0.03
    665
    +0.14
    0.03
    658
    +0.12
    0.02
    Negative Logits
    "]=>
    -0.97
    tenance
    -0.87
     Ago
    -0.82
    hub
    -0.82
    outer
    -0.81
    anwhile
    -0.80
    english
    -0.77
    read
    -0.77
    echo
    -0.77
     unden
    -0.77
    POSITIVE LOGITS
    İĭ
    0.96
     ideas
    0.95
    agnetic
    0.94
    éŃĶ
    0.93
     solutions
    0.91
     scraps
    0.87
     suggestions
    0.87
     excuses
    0.85
    efficients
    0.85
    umbnails
    0.84
    Activations Density 0.372%

    No Known Activations