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. 34506
    Prev
    Next
    INDEX
    Explanations

    texts related to writing and expressing opinions

    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
    567
    +0.18
    0.7%
    447
    +0.15
    0.6%
    330
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.18
    0.08
    396
    +0.15
    0.06
    636
    +0.13
    0.06
    Negative Logits
    ItemThumbnailImage
    -0.90
     granted
    -0.87
    seekers
    -0.86
    FML
    -0.84
    ão
    -0.81
     vantage
    -0.79
     Devices
    -0.79
    assetsadobe
    -0.79
     Authority
    -0.77
    htar
    -0.77
    POSITIVE LOGITS
     screenplay
    0.95
     diary
    0.88
     pulp
    0.88
     journals
    0.85
     journal
    0.84
     autobiography
    0.84
     aloud
    0.82
    ilk
    0.79
     slate
    0.78
     memoir
    0.78
    Activations Density 9.970%

    No Known Activations