© 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. 33286
    Prev
    Next
    INDEX
    Explanations

    phrases containing the phrase "When it comes to," typically followed by discussing various topics or issues

    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
    0.7%
    650
    +0.11
    0.5%
    183
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.18
    0.12
    195
    +0.11
    0.01
    566
    +0.10
    0.09
    Negative Logits
    oris
    -0.93
    wine
    -0.80
    vier
    -0.79
    essen
    -0.78
    iliary
    -0.77
    raid
    -0.76
    sav
    -0.75
     âĶľ
    -0.75
    ile
    -0.74
    boro
    -0.74
    POSITIVE LOGITS
     adversity
    0.77
     peril
    0.75
     tougher
    0.73
     true
    0.72
     raining
    0.72
     liner
    0.72
     apart
    0.70
     closer
    0.69
     alive
    0.69
     downhill
    0.68
    Activations Density 7.231%

    No Known Activations