© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25886
    Prev
    Next
    INDEX
    Explanations

    instances and references to active participation or engagement in various contexts

    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
    27
    +0.16
    0.9%
    508
    +0.14
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.16
    0.01
    325
    +0.14
    0.02
    141
    +0.14
    0.02
    Negative Logits
    ĥ½
    -2.42
    ĩ
    -2.41
    Ĥ¬
    -2.30
    Ł
    -2.15
    ŀ
    -2.15
    ļ
    -2.13
    į
    -2.09
    ¤
    -2.05
    §
    -2.03
    ĸ
    -2.02
    POSITIVE LOGITS
    tin
    1.64
    zo
    1.59
    NON
    1.48
    reon
    1.46
    rek
    1.45
    LAND
    1.44
     contrast
    1.38
     thick
    1.34
    fil
    1.34
    bred
    1.33
    Activations Density 0.218%

    No Known Activations