© 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. 27168
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "intelligence" 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
    376
    +0.13
    0.7%
    365
    +0.11
    0.6%
    72
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.13
    0.01
    83
    +0.11
    0.01
    495
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.38
    ©
    -2.23
    §
    -2.22
    ĨĴ
    -2.21
    ĵ
    -2.11
    ½
    -2.04
    ¯
    -2.02
    ³
    -2.02
    Į
    -1.98
    į
    -1.96
    POSITIVE LOGITS
     quarters
    1.84
     instruments
    1.66
     rests
    1.49
    holes
    1.47
    nal
    1.45
     areas
    1.45
    ships
    1.44
     chromatography
    1.44
    tight
    1.43
     experts
    1.43
    Activations Density 0.051%

    No Known Activations