© 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. 12983
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenging or difficult tasks

    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
    +0.19
    1.0%
    46
    +0.12
    0.6%
    732
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.19
    0.11
    119
    +0.12
    0.12
    77
    +0.09
    0.08
    Negative Logits
    nesty
    -0.68
    ificantly
    -0.62
    AZ
    -0.60
    andise
    -0.60
    erville
    -0.59
    ensional
    -0.59
    ellig
    -0.58
    tarian
    -0.58
    positive
    -0.58
    TextColor
    -0.57
    POSITIVE LOGITS
     slog
    0.99
     navigating
    0.86
     juggling
    0.85
     balancing
    0.78
     ardu
    0.77
     chore
    0.77
     daunting
    0.77
     navigate
    0.74
     task
    0.73
     trek
    0.72
    Activations Density 15.745%

    No Known Activations