© 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. 26118
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "NAME"

    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
    467
    +0.14
    0.8%
    269
    +0.12
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.14
    0.01
    394
    +0.12
    0.02
    58
    +0.12
    0.02
    Negative Logits
    ights
    -1.75
    ĥ½
    -1.50
     attendance
    -1.45
     Conduct
    -1.44
    .");
    -1.40
     experimentally
    -1.40
     considered
    -1.37
    ;}
    -1.37
     researching
    -1.36
     subscrib
    -1.35
    POSITIVE LOGITS
    ymb
    1.87
    cias
    1.85
    aho
    1.84
    esan
    1.84
    fest
    1.70
    ENCE
    1.70
    ég
    1.66
    worthy
    1.65
    smen
    1.61
    ball
    1.58
    Activations Density 0.015%

    No Known Activations