© 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. 34720
    Prev
    Next
    INDEX
    Explanations

    measurements and properties related to light, brightness, color, distance, sound, and environmental conditions

    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
    +0.22
    1.1%
    255
    +0.13
    0.7%
    481
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.22
    0.17
    160
    +0.13
    0.20
    640
    +0.10
    0.23
    Negative Logits
    bara
    -0.75
    irc
    -0.68
    ovie
    -0.67
    ctuary
    -0.66
    ullivan
    -0.63
    itled
    -0.63
    amar
    -0.62
    JECT
    -0.61
    igl
    -0.60
    nav
    -0.60
    POSITIVE LOGITS
     ranges
    0.75
     computed
    0.75
     increments
    0.75
     relative
    0.75
     gradient
    0.73
     ratio
    0.72
     difference
    0.72
     ratios
    0.72
     threshold
    0.71
     squared
    0.71
    Activations Density 10.939%

    No Known Activations