© 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. 39480
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and advice

    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
    182
    +0.10
    0.5%
    470
    +0.10
    0.5%
    246
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.10
    -0.04
    266
    +0.10
    0.24
    257
    +0.10
    0.07
    Negative Logits
    eder
    -0.74
    ledged
    -0.73
    apego
    -0.70
    livious
    -0.68
    wagon
    -0.67
    bage
    -0.66
    ruary
    -0.64
    ilts
    -0.64
    atio
    -0.63
    owship
    -0.63
    POSITIVE LOGITS
     FREE
    0.76
     TODAY
    0.73
     trending
    0.71
    Daily
    0.71
     Featured
    0.65
     curated
    0.65
     roundup
    0.64
     ï
    0.63
     Madden
    0.63
     infographic
    0.63
    Activations Density 8.774%

    No Known Activations