© 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. 13897
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical impact or influence

    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%
    538
    +0.07
    0.4%
    393
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.19
    0.32
    362
    +0.07
    0.22
    608
    +0.07
    0.25
    Negative Logits
    SPONSORED
    -0.77
    taboola
    -0.62
    keep
    -0.58
    ctuary
    -0.58
    yssey
    -0.58
    educated
    -0.58
    istries
    -0.57
    istry
    -0.57
    tenance
    -0.56
    inet
    -0.55
    POSITIVE LOGITS
     lightning
    0.92
     gunfire
    0.69
     arrows
    0.66
     mete
    0.61
     Paint
    0.58
     fire
    0.57
     seismic
    0.56
     bullets
    0.56
     blow
    0.56
     Falling
    0.56
    Activations Density 11.677%

    No Known Activations