© 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. 5406
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are sharing personal experiences or quoting conversations

    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
    +0.23
    1.1%
    566
    +0.21
    1.0%
    59
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.23
    0.15
    55
    +0.21
    0.13
    102
    +0.11
    0.11
    Negative Logits
    oyle
    -0.72
    edIn
    -0.70
     Which
    -0.69
    Entry
    -0.69
    -+-+
    -0.67
    inav
    -0.67
     ("
    -0.66
     entails
    -0.66
    ciation
    -0.66
    ESE
    -0.66
    POSITIVE LOGITS
     able
    1.16
    nt
    1.10
     supposed
    1.09
     fortunate
    1.08
     lucky
    1.01
    wolf
    1.01
     afraid
    1.00
    wolves
    1.00
     tempted
    1.00
     definitely
    0.99
    Activations Density 1.514%

    No Known Activations