© 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 Local
    5. 6-RES_SCL-AJT
    6. 13638
    Prev
    Next
    INDEX
    Explanations

    words related to events or actions reaching a conclusive or decisive point

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.28
    1.2%
    554
    +0.13
    0.6%
    151
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.28
    0.17
    393
    +0.13
    0.22
    718
    +0.11
    0.14
    Negative Logits
    lav
    -0.75
     Akin
    -0.74
    river
    -0.72
    pill
    -0.71
    maid
    -0.70
    amon
    -0.66
    folios
    -0.66
    icipated
    -0.65
    holders
    -0.65
    ung
    -0.65
    POSITIVE LOGITS
     reunited
    1.10
    éĹĺ
    0.96
     reun
    0.93
    icably
    0.91
     relent
    0.90
    FTWARE
    0.84
     reintrodu
    0.82
     finally
    0.81
     succeeded
    0.80
     succumbed
    0.80
    Activations Density 9.632%

    No Known Activations