© 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. 29866
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bark" and associated terms related to dogs

    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
    477
    +0.16
    0.9%
    115
    +0.12
    0.7%
    228
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.16
    0.01
    429
    +0.12
    0.01
    477
    +0.11
    0.01
    Negative Logits
    vers
    -1.44
    verts
    -1.43
     FIG
    -1.43
     Major
    -1.41
     charge
    -1.40
     time
    -1.39
     States
    -1.39
     happening
    -1.36
     tape
    -1.36
    verting
    -1.35
    POSITIVE LOGITS
    manship
    1.84
    eting
    1.69
    isms
    1.64
    endl
    1.63
    alta
    1.59
    ward
    1.54
    eson
    1.53
    iceps
    1.50
    ):
    1.49
    entes
    1.48
    Activations Density 0.030%

    No Known Activations