© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36342
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or disagreement

    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
    +0.36
    1.6%
    447
    +0.28
    1.2%
    362
    +0.23
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.36
    0.38
    385
    +0.28
    0.34
    393
    +0.23
    0.35
    Negative Logits
    uncle
    -0.91
    SPONSORED
    -0.88
    rand
    -0.82
    agu
    -0.75
    cum
    -0.74
    utm
    -0.73
    berus
    -0.73
    abella
    -0.72
    venture
    -0.72
    anan
    -0.72
    POSITIVE LOGITS
     rest
    1.17
     equation
    1.14
     same
    1.12
     remainder
    1.11
     confines
    1.10
     fray
    1.06
     entirety
    1.04
     door
    1.02
     proverbial
    1.01
     scene
    1.01
    Activations Density 9.611%

    No Known Activations