© 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. 26914
    Prev
    Next
    INDEX
    Explanations

    words related to a specific and repeated theme or character 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
    164
    +0.16
    0.9%
    348
    +0.13
    0.8%
    488
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.16
    0.03
    348
    +0.13
    0.03
    164
    +0.13
    0.02
    Negative Logits
    Ĥ
    -1.68
    »¿
    -1.63
    shore
    -1.60
    Ħ
    -1.60
    Ĺ
    -1.57
    ľ
    -1.53
    £
    -1.52
    ´
    -1.51
    ij
    -1.51
    İ
    -1.49
    POSITIVE LOGITS
    entin
    1.60
    ivo
    1.57
    eries
    1.53
    play
    1.50
    etry
    1.47
     Rptr
    1.44
    doi
    1.43
    Rptr
    1.40
    eval
    1.40
    itol
    1.39
    Activations Density 0.055%

    No Known Activations