© 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. 24185
    Prev
    Next
    INDEX
    Explanations

    historical dates and associated events

    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
    98
    +0.15
    0.9%
    157
    +0.14
    0.8%
    206
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.15
    0.03
    82
    +0.14
    0.02
    302
    +0.12
    0.03
    Negative Logits
     signatures
    -1.59
    imony
    -1.59
     descriptions
    -1.53
     historians
    -1.48
    umerable
    -1.47
     surviving
    -1.46
     representatives
    -1.44
     successor
    -1.42
    aments
    -1.41
     scholars
    -1.41
    POSITIVE LOGITS
    ){#
    2.13
    "}](#
    1.64
    CTYPE
    1.59
    stanbul
    1.59
    assis
    1.52
     Computing
    1.49
    )](#
    1.47
    monton
    1.45
    umin
    1.45
    irection
    1.44
    Activations Density 0.143%

    No Known Activations