© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27907
    Prev
    Next
    INDEX
    Explanations

    the acronym "CF" as it appears in various contexts

    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
    377
    +0.13
    0.8%
    376
    +0.13
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.13
    0.01
    417
    +0.13
    0.01
    70
    +0.12
    0.01
    Negative Logits
    Ļª
    -2.95
    ĨĴ
    -2.61
    ĻĤ
    -2.34
    ĥ½
    -2.34
    Ń
    -2.32
    ¯
    -2.21
    ¿½
    -2.19
    ľĵ
    -2.17
    ¶
    -2.14
    ¬
    -2.11
    POSITIVE LOGITS
    quart
    1.80
     filings
    1.67
    LET
    1.53
    ML
    1.45
    STA
    1.44
    ERC
    1.42
    strings
    1.41
    films
    1.39
    Ïģί
    1.36
    sheet
    1.33
    Activations Density 0.205%

    No Known Activations