© 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. 0-MLP-SM
    11. 25561
    Prev
    Next
    INDEX
    Explanations

    expressions of respect and admiration for individuals or groups

    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
    376
    +0.15
    0.8%
    274
    +0.11
    0.6%
    510
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.15
    0.02
    167
    +0.11
    0.02
    232
    +0.10
    0.01
    Negative Logits
    ·
    -3.16
    º
    -2.84
    ´
    -2.47
    Īĺ
    -2.45
    Ľ
    -2.39
    ¯
    -2.37
    ¹
    -2.33
    §
    -2.32
    «
    -2.27
    Ĺ
    -2.22
    POSITIVE LOGITS
    ably
    2.32
    ively
    1.64
    iative
    1.53
    ibly
    1.46
    ÃŃvel
    1.45
    able
    1.41
    ible
    1.40
    ivat
    1.39
     alia
    1.39
    ive
    1.38
    Activations Density 0.024%

    No Known Activations