Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4347
    Prev
    Next
    INDEX
    Explanations

    references to nighttime activities and settings

    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
    16
    +0.15
    0.6%
    459
    +0.14
    0.6%
    447
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.25
    649
    +0.14
    0.06
    422
    +0.13
    0.09
    Negative Logits
     Flavoring
    -0.98
    utical
    -0.88
    sbm
    -0.82
    apego
    -0.76
    edIn
    -0.73
    erella
    -0.72
    compl
    -0.71
    zb
    -0.71
    ocide
    -0.71
    ulner
    -0.71
    POSITIVE LOGITS
     vicinity
    1.09
     attic
    1.05
     courtyard
    1.03
     midst
    0.99
     enclosure
    0.98
     aisle
    0.92
     freezer
    0.90
     hallway
    0.88
     jungle
    0.88
     guise
    0.88
    Activations Density 10.999%

    No Known Activations