© 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. 26115
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ascend" or its variations

    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
    148
    +0.16
    0.9%
    46
    +0.14
    0.8%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.16
    0.01
    46
    +0.14
    0.01
    111
    +0.13
    0.01
    Negative Logits
    ingale
    -1.57
    ¿
    -1.50
    agers
    -1.49
    ters
    -1.47
    ĨĴ
    -1.45
    »¿
    -1.43
    ."_
    -1.41
     entire
    -1.41
     hardly
    -1.39
    ·¸
    -1.39
    POSITIVE LOGITS
    endant
    2.11
     ceil
    1.67
    endants
    1.59
    istar
    1.49
    ulous
    1.48
    itol
    1.45
    ulum
    1.40
    illin
    1.40
    vation
    1.40
    idium
    1.34
    Activations Density 0.037%

    No Known Activations