© 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. 34736
    Prev
    Next
    INDEX
    Explanations

    words related to clarity and transparency

    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
    +0.18
    0.8%
    459
    +0.13
    0.6%
    388
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.18
    0.09
    356
    +0.13
    0.02
    302
    +0.12
    0.09
    Negative Logits
     tremend
    -0.95
    eatures
    -0.84
     Loft
    -0.81
    unte
    -0.79
    uld
    -0.77
     therap
    -0.74
    inse
    -0.73
     nostalg
    -0.72
    LI
    -0.71
    olt
    -0.71
    POSITIVE LOGITS
    ances
    1.34
    ance
    1.06
    cut
    1.04
    cuts
    0.97
    iary
    0.88
     clear
    0.84
     indication
    0.83
     sailing
    0.82
     acrylic
    0.81
    headed
    0.80
    Activations Density 5.807%

    No Known Activations