© 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 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. 33405
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "transcribe" or related concepts like transcription and transliteration

    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
    130
    +0.10
    0.5%
    527
    +0.10
    0.5%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.23
    326
    +0.10
    0.20
    151
    +0.09
    0.14
    Negative Logits
    Reviewer
    -0.78
     è£ıè¦ļéĨĴ
    -0.66
    imentary
    -0.65
    imental
    -0.63
     Agenda
    -0.62
    iments
    -0.62
     Franch
    -0.62
    FACE
    -0.61
     Pelicans
    -0.60
     Sandy
    -0.60
    POSITIVE LOGITS
    ribed
    1.00
    okin
    0.96
    obal
    0.93
    oding
    0.92
    onduct
    0.89
    oded
    0.89
    ophon
    0.87
    ribing
    0.83
    ript
    0.82
    otomy
    0.81
    Activations Density 5.725%

    No Known Activations