© 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. 12966
    Prev
    Next
    INDEX
    Explanations

    ways or methods to address various problems or situations

    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
    92
    +0.10
    0.5%
    319
    +0.10
    0.5%
    273
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.10
    0.04
    596
    +0.10
    0.06
    455
    +0.10
    0.10
    Negative Logits
    ĸļ
    -0.94
    mare
    -0.78
    omore
    -0.77
    owship
    -0.77
    ulner
    -0.77
    usters
    -0.77
    rake
    -0.74
     Tanz
    -0.71
    ombie
    -0.67
    usher
    -0.67
    POSITIVE LOGITS
    finding
    0.82
    point
    0.78
    finder
    0.66
     altogether
    0.65
     inclined
    0.65
     ways
    0.64
    ward
    0.61
     ponies
    0.60
    terday
    0.59
     way
    0.59
    Activations Density 5.583%

    No Known Activations