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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27222
    Prev
    Next
    INDEX
    Explanations

    references to the country of Guinea

    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
    71
    +0.16
    0.9%
    453
    +0.12
    0.7%
    184
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.16
    0.01
    453
    +0.12
    0.01
    184
    +0.11
    0.01
    Negative Logits
    Ń
    -3.35
    ¸
    -3.23
    İ
    -3.19
    Ķ
    -3.17
    ľ
    -3.12
    ĨĴ
    -3.08
    Ħ
    -3.04
    į
    -3.04
    ¯
    -3.01
    ±
    -2.99
    POSITIVE LOGITS
    aceut
    1.85
    ify
    1.83
    ENTIAL
    1.72
    bolt
    1.66
    namese
    1.62
     striker
    1.61
    ual
    1.56
    shire
    1.56
    unto
    1.55
    velope
    1.55
    Activations Density 0.014%

    No Known Activations