© 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. 3902
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically related to sports events or personalities

    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
    351
    +0.03
    0.5%
    566
    +0.03
    0.5%
    438
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.03
    0.19
    288
    +0.03
    0.19
    526
    +0.02
    -0.03
    Negative Logits
     cov
    -0.16
    ially
    -0.15
     Castro
    -0.15
    terday
    -0.14
     spacing
    -0.13
    âĶĢâĶĢ
    -0.13
     constant
    -0.13
     imperfect
    -0.13
     istg
    -0.13
     overrun
    -0.13
    POSITIVE LOGITS
     Wag
    0.19
    stakes
    0.19
    gart
    0.18
    orno
    0.18
    hung
    0.18
    artisan
    0.18
    staff
    0.17
    liam
    0.17
    ocene
    0.17
    wana
    0.17
    Activations Density 5.226%

    No Known Activations