© 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. 25898
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "question"

    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
    320
    +0.11
    0.6%
    389
    +0.11
    0.6%
    120
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.11
    0.04
    389
    +0.11
    0.03
    60
    +0.10
    0.02
    Negative Logits
    ²
    -2.16
    ¤
    -1.80
    ľ
    -1.72
    )\\
    -1.65
    rile
    -1.58
     classics
    -1.55
    ĥ½
    -1.55
    ĻĤ
    -1.55
    µ
    -1.51
    ii
    -1.50
    POSITIVE LOGITS
     uncertain
    1.61
     others
    1.59
    "}](#
    1.53
    house
    1.49
    agles
    1.44
    ofl
    1.43
     unseen
    1.41
    odon
    1.38
    coat
    1.37
     Mueller
    1.37
    Activations Density 0.165%

    No Known Activations