© 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. 12748
    Prev
    Next
    INDEX
    Explanations

    specific locations or directions

    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
    393
    +0.11
    0.6%
    186
    +0.10
    0.5%
    679
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.11
    0.04
    595
    +0.10
    0.07
    393
    +0.09
    0.23
    Negative Logits
    ³³³³³³³³
    -0.53
     franc
    -0.51
    ouf
    -0.48
    oubted
    -0.47
    )].
    -0.46
     Doctrine
    -0.46
    ³³³³³³³³³³³³³³³³
    -0.46
    ³³³
    -0.46
    apt
    -0.45
     Feast
    -0.45
    POSITIVE LOGITS
    upon
    1.23
    abouts
    1.07
    fore
    1.06
    soever
    0.97
    with
    0.68
    ĪĴ
    0.66
    ¿½
    0.65
    £ı
    0.61
    rency
    0.60
    ngth
    0.60
    Activations Density 9.362%

    No Known Activations