© 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 EvalsExportsAPI 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. 24705
    Prev
    Next
    INDEX
    Explanations

    evidence of legal proceedings and case law references

    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
    500
    +0.11
    0.6%
    254
    +0.11
    0.6%
    97
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.11
    0.02
    380
    +0.11
    0.02
    348
    +0.11
    0.00
    Negative Logits
    ↵            ↵
    -3.50
    ↵
    -3.50
    -3.50
    <|outofrange|>
    -3.50
    č↵
    -3.50
    <|outofrange|>
    -3.50
    ↵
    -3.50
    -3.50
    -3.50
    ↵
    -3.50
    POSITIVE LOGITS
    zza
    1.81
    !’
    1.72
    ugh
    1.60
    ?’
    1.52
    ,’
    1.52
    let
    1.50
    .’”
    1.49
    ’.
    1.48
    ’,
    1.47
    encoded
    1.45
    Activations Density 0.200%

    No Known Activations