© 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. 30142
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character "p" in various contexts

    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
    369
    +0.16
    0.9%
    111
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.16
    0.01
    214
    +0.13
    0.01
    400
    +0.12
    0.01
    Negative Logits
    ismus
    -2.06
    terday
    -1.70
     matter
    -1.67
    ances
    -1.63
    acher
    -1.61
    ichael
    -1.57
    oming
    -1.56
    ás
    -1.56
    oxacin
    -1.55
    ise
    -1.55
    POSITIVE LOGITS
    ĨĴ
    2.08
     canon
    1.58
    inth
    1.52
    ĵ
    1.42
     induct
    1.36
     corner
    1.35
     prominently
    1.34
    »¿
    1.32
     recalling
    1.31
    GRect
    1.30
    Activations Density 0.450%

    No Known Activations