© 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. 26478
    Prev
    Next
    INDEX
    Explanations

    terminologies related to beer brewing and legal matters

    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
    156
    +0.41
    2.4%
    23
    +0.13
    0.7%
    138
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.41
    0.57
    473
    +0.13
    0.56
    49
    +0.12
    0.56
    Negative Logits
    blr
    -1.70
    dule
    -1.67
    cdn
    -1.51
    ){#
    -1.47
    emale
    -1.43
    izoph
    -1.40
    "){
    -1.39
    ugu
    -1.38
    eday
    -1.38
    аÐ
    -1.37
    POSITIVE LOGITS
     firmly
    1.46
     [@
    1.46
    ¦
    1.43
    fitting
    1.41
     light
    1.37
    inkling
    1.32
    orin
    1.30
    ²
    1.28
     estimated
    1.28
     attachment
    1.28
    Activations Density 2.891%

    No Known Activations