© 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. 25974
    Prev
    Next
    INDEX
    Explanations

    references to names or citations in a legal or formal 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/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
    421
    +0.15
    0.9%
    242
    +0.12
    0.6%
    73
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.15
    0.22
    74
    +0.12
    0.14
    222
    +0.10
    0.16
    Negative Logits
    (@"
    -1.52
    cludes
    -1.52
    ())
    -1.47
     )$
    -1.41
     '</
    -1.41
    private
    -1.40
    ))$
    -1.39
     typedef
    -1.38
    popular
    -1.37
    zyk
    -1.37
    POSITIVE LOGITS
    weight
    1.68
    holm
    1.61
    garten
    1.53
     shocks
    1.45
    haus
    1.44
    naire
    1.43
    naments
    1.42
    worker
    1.40
    matter
    1.38
     influenza
    1.34
    Activations Density 1.566%

    No Known Activations