© 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. 39770
    Prev
    Next
    INDEX
    Explanations

    comparisons between different concepts or scenarios

    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
    +0.24
    1.4%
    75
    +0.09
    0.5%
    647
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.24
    0.25
    138
    +0.09
    0.23
    64
    +0.08
    -0.18
    Negative Logits
    icators
    -0.64
    icator
    -0.63
    iyah
    -0.60
    ulty
    -0.59
    aii
    -0.58
    overy
    -0.58
    icity
    -0.57
    ainer
    -0.56
    idates
    -0.55
    ellen
    -0.55
    POSITIVE LOGITS
    lihood
    1.01
    liest
    0.91
    lier
    0.86
     ours
    0.72
    liness
    0.63
     hers
    0.57
     mirror
    0.55
     unto
    0.55
     wildfire
    0.54
     scissors
    0.53
    Activations Density 9.645%

    No Known Activations