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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3860
    Prev
    Next
    INDEX
    Explanations

    numerical references to the number 90

    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
    488
    +0.13
    0.6%
    311
    +0.13
    0.6%
    461
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.13
    0.09
    352
    +0.13
    0.14
    127
    +0.12
    0.10
    Negative Logits
    wan
    -0.82
    lish
    -0.81
    board
    -0.81
    lay
    -0.80
    pocket
    -0.78
    friend
    -0.76
    maid
    -0.73
    Redd
    -0.72
    plant
    -0.71
    seeing
    -0.71
    POSITIVE LOGITS
     degrees
    0.84
    idth
    0.83
    orsi
    0.82
    80
    0.78
    istries
    0.78
    issions
    0.78
    %:
    0.77
    anwhile
    0.76
    terday
    0.75
    º
    0.75
    Activations Density 8.788%

    No Known Activations