© 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. 29854
    Prev
    Next
    INDEX
    Explanations

    references to paragraphs in text

    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
    +0.18
    1.0%
    156
    +0.16
    0.9%
    164
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    89
    +0.18
    0.01
    25
    +0.16
    0.01
    463
    +0.12
    0.01
    Negative Logits
    ĥ½
    -4.34
    ľĵ
    -4.25
    ©
    -4.07
    §
    -4.06
    ¼
    -4.06
    ½
    -4.04
    ·
    -3.99
    ĵ
    -3.96
    Ī
    -3.96
    ↵
    -3.93
    POSITIVE LOGITS
    aments
    1.63
     msgid
    1.57
     notes
    1.57
    manship
    1.49
    cule
    1.48
     chromatography
    1.47
    tight
    1.47
    gap
    1.44
    ttes
    1.44
    series
    1.42
    Activations Density 0.020%

    No Known Activations