© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33421
    Prev
    Next
    INDEX
    Explanations

    words related to lighting, including terms such as "lighting changes," "exposure," "shadows," and "sunlight."

    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
    0.9%
    326
    +0.13
    0.6%
    553
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.23
    288
    +0.13
    0.23
    557
    +0.11
    0.08
    Negative Logits
    llah
    -0.86
    books
    -0.68
    ciating
    -0.65
    arnaev
    -0.64
    WER
    -0.63
    clair
    -0.63
    dinand
    -0.61
    TAIN
    -0.61
    zanne
    -0.61
    ilage
    -0.61
    POSITIVE LOGITS
     bulbs
    0.94
     lights
    0.88
     bulb
    0.87
     lighting
    0.85
     illuminated
    0.83
    lights
    0.82
     lamps
    0.80
     emitting
    0.78
     brighter
    0.78
     illuminate
    0.78
    Activations Density 9.202%

    No Known Activations