© 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. 14038
    Prev
    Next
    INDEX
    Explanations

    information about operating hours and availability of various establishments and services

    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
    295
    +0.15
    0.7%
    388
    +0.13
    0.6%
    447
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.15
    0.08
    84
    +0.13
    0.04
    665
    +0.12
    0.12
    Negative Logits
    Catalog
    -0.81
    Sol
    -0.67
    ILA
    -0.66
    Publisher
    -0.65
    Filename
    -0.64
    Frag
    -0.64
    cest
    -0.62
    ĪĴ
    -0.62
    PART
    -0.61
    Ī
    -0.60
    POSITIVE LOGITS
     indefinitely
    0.89
     alive
    0.74
    abouts
    0.73
     temporarily
    0.71
     forever
    0.68
     insured
    0.68
     leases
    0.68
     Mondays
    0.68
     till
    0.67
    figured
    0.67
    Activations Density 6.605%

    No Known Activations