© 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. 32618
    Prev
    Next
    INDEX
    Explanations

    words related to trading, economics, and commodities

    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
    739
    +0.07
    0.7%
    456
    +0.07
    0.6%
    640
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.26
    575
    +0.07
    0.16
    326
    +0.06
    0.20
    Negative Logits
    loo
    -0.43
    ttp
    -0.40
    arta
    -0.35
    atten
    -0.35
    omes
    -0.34
    borough
    -0.32
    aan
    -0.32
    ruck
    -0.31
    coming
    -0.31
    kj
    -0.31
    POSITIVE LOGITS
     commod
    0.39
    eering
    0.38
    eers
    0.37
    rolet
    0.36
    ourgeois
    0.35
    rous
    0.33
    isites
    0.33
    ality
    0.33
    eer
    0.33
    ization
    0.32
    Activations Density 6.244%

    No Known Activations