© 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. 31594
    Prev
    Next
    INDEX
    Explanations

    descriptive details related to auditory and sensory experiences

    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
    +0.16
    0.7%
    178
    +0.10
    0.4%
    702
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    749
    +0.16
    0.11
    154
    +0.10
    0.15
    326
    +0.10
    0.29
    Negative Logits
    folios
    -1.08
    folio
    -0.93
    ardless
    -0.88
     portfolios
    -0.85
    ãĤ¤ãĥĪ
    -0.74
    utton
    -0.73
    icient
    -0.72
    ilege
    -0.72
    reenshots
    -0.72
    ritional
    -0.71
    POSITIVE LOGITS
     noises
    1.38
     louder
    1.29
     audible
    1.24
     chants
    1.13
     loudly
    1.12
     sounded
    1.12
     echoing
    1.12
     footsteps
    1.11
     emanating
    1.11
     reverber
    1.10
    Activations Density 14.791%

    No Known Activations