Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27553
    Prev
    Next
    INDEX
    Explanations

    references to hands or palm-related imagery

    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
    148
    +0.12
    0.7%
    104
    +0.12
    0.6%
    448
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.12
    0.01
    104
    +0.12
    0.01
    409
    +0.11
    0.01
    Negative Logits
    illance
    -1.58
    rian
    -1.56
    rians
    -1.51
    mia
    -1.51
     simplest
    -1.45
    ĥ
    -1.45
    rations
    -1.38
    duction
    -1.38
    jection
    -1.37
    fections
    -1.36
    POSITIVE LOGITS
    notes
    1.95
    istry
    1.89
    istor
    1.85
    ilion
    1.75
    stone
    1.75
    istically
    1.74
    ier
    1.71
    caster
    1.69
    chair
    1.65
    iers
    1.65
    Activations Density 0.012%

    No Known Activations