© 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. 12986
    Prev
    Next
    INDEX
    Explanations

    different ways to approach a situation or solve a problem

    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
    +0.20
    1.0%
    453
    +0.11
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.20
    0.03
    114
    +0.11
    0.08
    263
    +0.10
    0.07
    Negative Logits
    usters
    -0.68
    ieu
    -0.67
    vertisement
    -0.65
    IFIED
    -0.63
    inately
    -0.63
    raid
    -0.63
    inally
    -0.63
    ulus
    -0.62
    uminati
    -0.62
    uster
    -0.61
    POSITIVE LOGITS
    finding
    0.91
    cale
    0.86
    eries
    0.77
    paces
    0.71
    styles
    0.69
     ways
    0.69
    heet
    0.68
    pointers
    0.67
     Ways
    0.67
    etting
    0.67
    Activations Density 12.114%

    No Known Activations