© 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. 14012
    Prev
    Next
    INDEX
    Explanations

    statements related to politics, corruption, and research studies

    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
    480
    +0.52
    5.1%
    447
    +0.30
    2.9%
    481
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.52
    0.03
    266
    +0.30
    0.49
    351
    +0.05
    0.10
    Negative Logits
    )?
    -0.44
    )!
    -0.37
    ependence
    -0.29
    >)
    -0.29
    ))))
    -0.29
    )--
    -0.29
     partName
    -0.28
    !).
    -0.28
     meanwhile
    -0.28
    '?
    -0.28
    POSITIVE LOGITS
     "âĢ¦
    0.39
     "'
    0.35
     "...
    0.33
     "[
    0.32
     "#
    0.31
     "
    0.29
     Cipher
    0.26
     Blumenthal
    0.24
     ""
    0.24
     "+
    0.24
    Activations Density 30.824%

    No Known Activations