© 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
    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. 14008
    Prev
    Next
    INDEX
    Explanations

    measurements of dimensions and quantities in international units

    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
    507
    +0.13
    0.5%
    565
    +0.11
    0.4%
    655
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.13
    0.10
    314
    +0.11
    -0.00
    220
    +0.10
    0.11
    Negative Logits
     guiName
    -0.92
    edIn
    -0.92
    HAHAHAHA
    -0.82
    earchers
    -0.78
    rarily
    -0.77
    lio
    -0.75
    ernaut
    -0.74
    otiation
    -0.74
    anan
    -0.73
    rompt
    -0.72
    POSITIVE LOGITS
    %)
    1.50
    ),"
    1.44
    %).
    1.30
    %),
    1.28
    )
    1.25
    )."
    1.25
    )",
    1.25
    )—
    1.25
    )-
    1.24
    )--
    1.24
    Activations Density 5.377%

    No Known Activations