© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29026
    Prev
    Next
    INDEX
    Explanations

    instances of the term "Grav" or related keywords in the context of technology and educational environments

    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
    +0.15
    0.8%
    164
    +0.13
    0.7%
    317
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.15
    0.01
    111
    +0.13
    0.01
    134
    +0.12
    0.01
    Negative Logits
    ¯
    -2.47
    ĸ´
    -2.44
    »
    -2.43
    ¸
    -2.38
    ↵↵
    -2.37
    ↵
    -2.37
    <|outofrange|>
    -2.37
    -2.37
    -2.37
     ↵
    -2.37
    POSITIVE LOGITS
    ibase
    1.88
    itat
    1.77
    stones
    1.63
    estone
    1.62
    isecond
    1.62
    estones
    1.61
    hetto
    1.48
    iseconds
    1.47
    FW
    1.41
    ************************************************************************
    1.40
    Activations Density 0.006%

    No Known Activations