© 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. 27165
    Prev
    Next
    INDEX
    Explanations

    the term "Live" as it relates to events or streaming content

    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
    +0.17
    1.0%
    476
    +0.11
    0.6%
    201
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.17
    0.02
    474
    +0.11
    0.01
    65
    +0.10
    0.02
    Negative Logits
    Ń
    -2.72
    §
    -2.63
    Ĥ
    -2.52
    ¯
    -2.52
    ³
    -2.48
    ľĵ
    -2.43
    ľ
    -2.41
    Ĥ¬
    -2.31
    ¶
    -2.22
    ·
    -2.18
    POSITIVE LOGITS
    hoc
    1.84
    inson
    1.74
    aby
    1.70
    acle
    1.69
    venth
    1.65
    vision
    1.64
     needs
    1.62
    forge
    1.62
    chet
    1.62
    recht
    1.59
    Activations Density 0.015%

    No Known Activations