© 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 Local
    9. 6-RES_SCL-AJT
    11. 13790
    Prev
    Next
    INDEX
    Explanations

    text related to events and schedules

    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
    247
    +0.03
    0.6%
    526
    +0.02
    0.5%
    383
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.03
    0.32
    373
    +0.02
    -0.21
    649
    +0.02
    0.06
    Negative Logits
     combust
    -0.14
    FUN
    -0.14
    FORM
    -0.14
     splits
    -0.13
     RELE
    -0.13
    âķIJâķIJ
    -0.13
    spin
    -0.13
     lanes
    -0.13
     anchors
    -0.13
     loops
    -0.13
    POSITIVE LOGITS
    atchewan
    0.18
    racuse
    0.17
    isSpecialOrderable
    0.17
    iston
    0.17
     challeng
    0.16
     Strongh
    0.16
    ratulations
    0.16
    rontal
    0.16
    »Ĵ
    0.16
    ãĤ´ãĥ³
    0.15
    Activations Density 10.175%

    No Known Activations