© 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
    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. 14346
    Prev
    Next
    INDEX
    Explanations

    technical terms and content related to technology, setup instructions and activities like coding and language functions

    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
    107
    +0.04
    0.5%
    709
    +0.03
    0.5%
    243
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.04
    0.03
    746
    +0.03
    0.01
    604
    +0.03
    0.01
    Negative Logits
     Orthodox
    -0.18
     instruct
    -0.18
     âĢİ
    -0.18
     nearest
    -0.18
     transcripts
    -0.18
     plasma
    -0.18
     isEnabled
    -0.17
     ·
    -0.17
     LEVEL
    -0.17
    brate
    -0.17
    POSITIVE LOGITS
     proverb
    0.25
    nw
    0.24
    ovember
    0.24
    sworth
    0.24
    loo
    0.23
     Hoo
    0.23
    aum
    0.22
     sugg
    0.22
    ischer
    0.22
    yout
    0.21
    Activations Density 0.042%

    No Known Activations