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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22871
    Prev
    Next
    INDEX
    Explanations

    instances of sharing and community involvement

    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
    179
    +0.13
    0.7%
    153
    +0.12
    0.7%
    320
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.13
    0.07
    33
    +0.12
    0.06
    170
    +0.12
    0.06
    Negative Logits
    ?
    -1.61
    ?!
    -1.60
    ime
    -1.44
     Amer
    -1.42
     Well
    -1.37
    )?
    -1.31
    ientes
    -1.31
    chu
    -1.30
    anza
    -1.29
     Hum
    -1.29
    POSITIVE LOGITS
    ĥ½
    4.29
    <|outofrange|>
    3.90
    ↵
    3.90
     ↵
    3.90
    č↵
    3.90
     ↵
    3.90
    3.90
    <|outofrange|>
    3.90
    <|outofrange|>
    3.90
    č↵
    3.90
    Activations Density 1.207%

    No Known Activations