© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28603
    Prev
    Next
    INDEX
    Explanations

    references to pulp fiction or pulp magazines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.14
    0.8%
    91
    +0.13
    0.7%
    257
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.14
    0.01
    230
    +0.13
    0.01
    91
    +0.12
    0.01
    Negative Logits
    ķ
    -2.99
    ĥ
    -2.85
    ĥ½
    -2.82
    ı
    -2.82
    Ń
    -2.76
    ½
    -2.76
    ĵ
    -2.67
    ľĵ
    -2.66
    Ĥ
    -2.63
    Ĭ
    -2.58
    POSITIVE LOGITS
     recalls
    1.87
    istry
    1.76
    tight
    1.66
    inus
    1.65
    ious
    1.64
    eries
    1.63
    ist
    1.61
    yard
    1.59
    film
    1.57
    illar
    1.56
    Activations Density 0.014%

    No Known Activations