© 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 EvalsExportsAPI 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. 29168
    Prev
    Next
    INDEX
    Explanations

    references to player recognition and achievements

    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
    211
    +0.16
    1.0%
    376
    +0.13
    0.8%
    193
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.16
    0.01
    193
    +0.13
    0.01
    277
    +0.12
    0.01
    Negative Logits
    ĥ½
    -1.90
    ·
    -1.83
    woke
    -1.67
    §
    -1.60
    ³
    -1.57
     transgender
    -1.52
    Ń
    -1.51
    ĺ
    -1.50
     my
    -1.49
    «
    -1.47
    POSITIVE LOGITS
    's
    1.75
    het
    1.74
    ful
    1.60
    ious
    1.59
    house
    1.58
    pieces
    1.56
    ÃŃs
    1.55
     rests
    1.50
    craft
    1.50
    strings
    1.49
    Activations Density 0.070%

    No Known Activations