© 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. 40525
    Prev
    Next
    INDEX
    Explanations

    names of cities or places

    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
    571
    +0.08
    0.6%
    68
    +0.06
    0.5%
    150
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.08
    0.23
    288
    +0.06
    0.23
    99
    +0.06
    0.10
    Negative Logits
    istically
    -0.57
    opol
    -0.47
    ahime
    -0.46
     Genie
    -0.45
     Strait
    -0.45
    ophe
    -0.44
    ozy
    -0.43
    */(
    -0.43
    istics
    -0.42
    riel
    -0.42
    POSITIVE LOGITS
     Sheffield
    0.46
    ffield
    0.41
    ivable
    0.41
     Bunny
    0.40
     Kund
    0.40
     Ki
    0.39
    bugs
    0.37
    sburg
    0.36
     Hanson
    0.36
     Hutchinson
    0.36
    Activations Density 9.133%

    No Known Activations