© 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. 2-MLP-SM
    11. 26071
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating ability or potential

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    395
    +0.13
    0.7%
    84
    +0.12
    0.7%
    2
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.13
    0.04
    337
    +0.12
    0.03
    297
    +0.11
    0.04
    Negative Logits
    ITED
    -1.72
    idyl
    -1.70
    onitrile
    -1.52
    OO
    -1.48
    printStackTrace
    -1.48
     magnitude
    -1.43
     yours
    -1.42
    osity
    -1.41
     ***
    -1.40
     Redistributions
    -1.39
    POSITIVE LOGITS
    »
    2.32
    »¿
    2.22
    ·
    1.84
    1.82
    ↵↵
    1.82
    1.82
    ↵  ³³³
    1.82
    ↵↵
    1.82
    <|outofrange|>
    1.82
    <|outofrange|>
    1.82
    Activations Density 0.137%

    No Known Activations