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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 45429
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "millennials"

    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
    +0.14
    0.8%
    288
    +0.12
    0.7%
    193
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.14
    0.04
    660
    +0.12
    0.08
    649
    +0.11
    0.02
    Negative Logits
    lessly
    -0.65
    idon
    -0.60
    ãĥ¯
    -0.60
    etr
    -0.59
    manship
    -0.59
    NEY
    -0.57
    iasis
    -0.55
    fman
    -0.55
    unal
    -0.54
    pex
    -0.53
    POSITIVE LOGITS
     Millenn
    0.68
     millennials
    0.67
     generation
    0.64
     Millennials
    0.62
     millennial
    0.62
     adulthood
    0.59
    ennial
    0.58
     cohort
    0.57
    uates
    0.55
     turnout
    0.54
    Activations Density 10.730%

    No Known Activations