© 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. 27192
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain only sequences of '#' characters

    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
    29
    +0.14
    0.8%
    111
    +0.13
    0.8%
    108
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.01
    29
    +0.13
    0.01
    131
    +0.13
    0.01
    Negative Logits
    »
    -2.20
    ľ
    -2.13
    ¿
    -2.09
    ı
    -2.08
    ª
    -2.04
    ¿½
    -1.97
    ´
    -1.96
    ·¸
    -1.91
    ĥ
    -1.85
    ¶
    -1.84
    POSITIVE LOGITS
    amble
    1.84
    ulations
    1.78
    erne
    1.66
    aria
    1.59
    rpm
    1.56
    ards
    1.55
    edly
    1.55
    krit
    1.55
    cards
    1.55
    arium
    1.54
    Activations Density 0.352%

    No Known Activations