© 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. 26572
    Prev
    Next
    INDEX
    Explanations

    lines or sections of text that denote a break or separator in a document

    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
    410
    +0.13
    0.7%
    111
    +0.13
    0.7%
    258
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.01
    454
    +0.13
    0.01
    410
    +0.12
    0.01
    Negative Logits
     controlled
    -1.63
     hybridization
    -1.51
    icer
    -1.49
    )].
    -1.44
     functioning
    -1.40
    hin
    -1.39
    forming
    -1.39
     transplantation
    -1.39
     tuned
    -1.37
     Modified
    -1.36
    POSITIVE LOGITS
    ppo
    1.68
    anks
    1.60
    !,
    1.59
    êt
    1.58
    endas
    1.56
    agons
    1.53
    ças
    1.51
    {}{
    1.50
    ól
    1.49
    rics
    1.49
    Activations Density 0.010%

    No Known Activations