© 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
    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. 1464
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and concepts

    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
    322
    +0.13
    0.5%
    537
    +0.12
    0.5%
    525
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.13
    0.12
    152
    +0.12
    0.12
    124
    +0.11
    0.10
    Negative Logits
    ulhu
    -0.95
     Continental
    -0.79
    PsyNetMessage
    -0.77
     Hicks
    -0.77
     Dunk
    -0.77
     Pompe
    -0.76
     aboard
    -0.75
     Kern
    -0.75
     Peoples
    -0.75
     cir
    -0.74
    POSITIVE LOGITS
    sized
    1.27
    scale
    1.18
    selling
    1.17
    based
    1.16
    centric
    1.15
    tun
    1.13
    tier
    1.11
    tailed
    1.08
    specific
    1.07
    sharing
    1.07
    Activations Density 1.206%

    No Known Activations