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. 27540
    Prev
    Next
    INDEX
    Explanations

    recurring conjunctions in a list context

    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
    247
    +0.12
    0.7%
    369
    +0.11
    0.6%
    39
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.12
    0.45
    209
    +0.11
    0.29
    402
    +0.11
    0.26
    Negative Logits
    errals
    -1.68
    alus
    -1.67
    iterr
    -1.57
    eson
    -1.55
    engers
    -1.54
    ackets
    -1.48
    onica
    -1.45
    acters
    -1.43
    etts
    -1.43
    tingham
    -1.41
    POSITIVE LOGITS
    Ĥ¬
    2.92
    µ
    2.79
    ½
    2.79
    ķ
    2.75
    Ĺ
    2.73
    IJ
    2.73
    ¿
    2.70
    §
    2.68
    ĸ´
    2.67
    ¯
    2.63
    Activations Density 1.569%

    No Known Activations