© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27812
    Prev
    Next
    INDEX
    Explanations

    the presence of method declarations in code

    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
    371
    +0.13
    0.8%
    35
    +0.13
    0.7%
    165
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.13
    0.11
    371
    +0.13
    0.12
    18
    +0.12
    0.08
    Negative Logits
    "}](#
    -1.65
    olate
    -1.55
     (`
    -1.51
     chromatography
    -1.46
     ([
    -1.41
     unsupported
    -1.41
    hee
    -1.39
     ($
    -1.38
     mic
    -1.36
    keeping
    -1.34
    POSITIVE LOGITS
    ings
    1.57
    rose
    1.55
    deal
    1.50
    speech
    1.49
    oise
    1.46
    roy
    1.45
    ruce
    1.36
    vens
    1.36
    chle
    1.35
    know
    1.35
    Activations Density 3.443%

    No Known Activations