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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25990
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "one"

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    307
    +0.12
    0.7%
    128
    +0.12
    0.6%
    271
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.07
    307
    +0.12
    0.04
    128
    +0.11
    0.03
    Negative Logits
     Parenthood
    -1.89
     alia
    -1.59
    GMP
    -1.49
    (@
    -1.44
    !(
    -1.42
     OK
    -1.40
    (:
    -1.40
    erate
    -1.37
    lists
    -1.36
    iates
    -1.36
    POSITIVE LOGITS
    onic
    1.72
     Tower
    1.54
    quart
    1.47
    iscus
    1.46
    ault
    1.41
     wing
    1.41
    ulp
    1.38
     slash
    1.37
     Chamber
    1.37
     quarter
    1.36
    Activations Density 0.334%

    No Known Activations