© 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. 32532
    Prev
    Next
    INDEX
    Explanations

    phrases related to price matching and comparisons between different entities or characteristics

    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
    0.9%
    187
    +0.11
    0.5%
    255
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.18
    0.10
    446
    +0.11
    0.09
    9
    +0.10
    0.09
    Negative Logits
    irtual
    -0.76
    raq
    -0.72
    cember
    -0.67
    cation
    -0.66
    hement
    -0.64
    ################################
    -0.64
    cknow
    -0.62
    duc
    -0.60
    Directory
    -0.58
    ä¼
    -0.58
    POSITIVE LOGITS
    ioned
    0.73
     match
    0.70
     matches
    0.70
    ees
    0.70
     Match
    0.68
    sticks
    0.63
     CLSID
    0.62
     matched
    0.62
    maker
    0.62
     McCann
    0.61
    Activations Density 8.563%

    No Known Activations