© 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. 25867
    Prev
    Next
    INDEX
    Explanations

    references to art and culture, particularly in academic 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
    17
    +0.14
    0.8%
    54
    +0.12
    0.6%
    496
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.14
    0.15
    496
    +0.12
    0.14
    33
    +0.11
    0.14
    Negative Logits
    ]:
    -1.63
    genstein
    -1.52
    cient
    -1.52
    ke
    -1.49
    schild
    -1.48
    lay
    -1.48
    ius
    -1.45
    ko
    -1.43
    stein
    -1.39
    hood
    -1.37
    POSITIVE LOGITS
    ľĵ
    3.18
    »¿
    2.58
    Ĺ
    2.44
    Ļ
    2.39
    ĨĴ
    2.38
    ı
    2.27
    Ł
    2.26
    Ľ
    2.21
    ¡
    2.20
    IJ
    2.20
    Activations Density 3.710%

    No Known Activations