© 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. 13672
    Prev
    Next
    INDEX
    Explanations

    information related to books and references

    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
    640
    +0.58
    2.2%
    160
    +0.14
    0.5%
    132
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.58
    0.28
    64
    +0.14
    -0.08
    615
    +0.11
    0.12
    Negative Logits
    ndra
    -1.03
    uca
    -1.01
    ardless
    -0.99
    utics
    -0.98
    ossip
    -0.96
    hement
    -0.94
    aterasu
    -0.94
    igans
    -0.93
    sterdam
    -0.93
    illance
    -0.92
    POSITIVE LOGITS
    âĵĺ
    1.46
    Appearances
    1.31
    Trivia
    1.29
    Example
    1.11
    pmwiki
    1.11
    Optional
    1.08
    Official
    1.08
    Notes
    1.08
    References
    1.08
    Various
    1.07
    Activations Density 1.799%

    No Known Activations