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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27924
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'C' in various contexts

    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
    369
    +0.33
    1.9%
    156
    +0.17
    1.0%
    196
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.33
    0.08
    196
    +0.17
    0.07
    373
    +0.12
    0.06
    Negative Logits
    ↵↵
    -3.10
     ↵
    -3.10
    č↵
    -3.10
    ↵
    -3.10
    ↵
    -3.10
    -3.10
    -3.10
    <|padding|>
    -3.10
    -3.10
    -3.10
    POSITIVE LOGITS
    UST
    1.67
    redited
    1.65
    otted
    1.49
    abi
    1.46
     NMR
    1.43
    SI
    1.43
     experimentally
    1.41
    UB
    1.41
     together
    1.41
     smear
    1.39
    Activations Density 8.297%

    No Known Activations