© 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. 14240
    Prev
    Next
    INDEX
    Explanations

    references to starting something from the beginning or creating something new from the very basic level

    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
    +0.20
    1.0%
    651
    +0.13
    0.6%
    302
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.20
    0.11
    526
    +0.13
    -0.07
    636
    +0.12
    0.06
    Negative Logits
    agonist
    -0.77
    CVE
    -0.69
    uned
    -0.66
    quickShipAvailable
    -0.66
    ossession
    -0.66
     Osw
    -0.65
    rid
    -0.63
    anchester
    -0.62
    acl
    -0.60
    amide
    -0.60
    POSITIVE LOGITS
     scratch
    0.99
     scratched
    0.89
    pad
    0.85
    manship
    0.84
    eting
    0.83
     slate
    0.76
    ratch
    0.75
    beat
    0.73
    berry
    0.72
    bones
    0.71
    Activations Density 9.182%

    No Known Activations