© 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. 4895
    Prev
    Next
    INDEX
    Explanations

    references to technical programming terms and descriptions

    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
    481
    +0.19
    0.9%
    447
    +0.14
    0.7%
    431
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.33
    575
    +0.14
    0.23
    225
    +0.10
    0.15
    Negative Logits
    £ı
    -0.81
    姫
    -0.73
    Ļ½
    -0.72
    Weather
    -0.68
     provincial
    -0.65
    rake
    -0.60
    ornings
    -0.60
    Saharan
    -0.60
    urban
    -0.59
    Fax
    -0.57
    POSITIVE LOGITS
     itself
    0.98
    osphere
    0.74
    forts
    0.72
    liest
    0.71
     theorem
    0.68
    mma
    0.65
    iest
    0.64
     portion
    0.64
    ocalypse
    0.64
    ariat
    0.64
    Activations Density 11.473%

    No Known Activations