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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1432
    Prev
    Next
    INDEX
    Explanations

    instances where something runs out or is limited in supply

    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
    627
    +0.17
    0.6%
    322
    +0.15
    0.5%
    678
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.17
    0.03
    322
    +0.15
    0.04
    236
    +0.14
    0.04
    Negative Logits
    ramid
    -1.17
     Pillar
    -1.07
    htaking
    -1.06
    hemy
    -1.04
    ©¶æ
    -1.03
    heed
    -1.02
     Directorate
    -1.00
     emblem
    -0.97
    iate
    -0.96
    gemony
    -0.92
    POSITIVE LOGITS
     patience
    1.39
     supplies
    1.26
    ventory
    1.24
     supply
    1.19
     capacity
    1.07
     Braun
    1.05
    arcity
    1.05
     inventory
    1.02
     tolerance
    1.00
     calories
    0.99
    Activations Density 0.791%

    No Known Activations