© 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. 0-MLP-SM
    11. 27667
    Prev
    Next
    INDEX
    Explanations

    mentions of fantasy as a genre or theme 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/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
    156
    +0.29
    1.7%
    71
    +0.13
    0.8%
    377
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.29
    0.02
    231
    +0.13
    0.02
    74
    +0.13
    0.01
    Negative Logits
     ticket
    -1.44
     same
    -1.41
    ori
    -1.37
     trusted
    -1.36
     success
    -1.35
     donate
    -1.34
    еÑģ
    -1.34
    ERT
    -1.33
    ott
    -1.32
    ritic
    -1.32
    POSITIVE LOGITS
    istically
    2.10
    wise
    1.83
    ontally
    1.70
    ignment
    1.64
    "}](#
    1.60
    ually
    1.57
    keeping
    1.55
    itious
    1.55
    illac
    1.51
    kill
    1.44
    Activations Density 0.015%

    No Known Activations