© 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. 26034
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hitting" and its variations in different 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
    376
    +0.17
    0.9%
    444
    +0.14
    0.7%
    148
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.17
    0.01
    282
    +0.14
    0.01
    457
    +0.13
    0.01
    Negative Logits
    imab
    -1.83
     becoming
    -1.53
     developing
    -1.44
    enza
    -1.44
    si
    -1.39
    oles
    -1.34
    adors
    -1.31
    urs
    -1.31
    llll
    -1.31
    ners
    -1.29
    POSITIVE LOGITS
    tons
    1.86
     ]"
    1.67
     )"
    1.60
     contradiction
    1.53
     difficulties
    1.51
    worm
    1.49
    fault
    1.48
    curve
    1.46
    backslash
    1.46
    sects
    1.44
    Activations Density 0.021%

    No Known Activations