© 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 EvalsExportsinterp-engineNEWAPI 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. 32335
    Prev
    Next
    INDEX
    Explanations

    mention of polar bears or related topics

    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
    288
    +0.18
    0.8%
    578
    +0.18
    0.7%
    421
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.18
    0.01
    288
    +0.18
    0.18
    326
    +0.14
    0.20
    Negative Logits
    bler
    -0.88
    hig
    -0.86
    ptroller
    -0.86
    ECH
    -0.83
    alach
    -0.82
    lished
    -0.82
    rahim
    -0.81
    eem
    -0.79
    ITNESS
    -0.78
    LER
    -0.78
    POSITIVE LOGITS
     vortex
    1.01
     polar
    1.00
    izing
    0.96
     oppos
    0.91
    ities
    0.88
     Polar
    0.87
    ising
    0.86
    oid
    0.85
     bear
    0.84
    itary
    0.83
    Activations Density 6.779%

    No Known Activations