© 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 EvalsExportsinterp-engineNEWAPI 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. 25989
    Prev
    Next
    INDEX
    Explanations

    references to specific materials in scientific 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
    392
    +0.13
    0.8%
    360
    +0.13
    0.8%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.13
    0.03
    53
    +0.13
    0.03
    56
    +0.12
    0.01
    Negative Logits
    Ĭ
    -2.65
    §
    -2.63
    ©
    -2.61
    ĥ
    -2.59
    ³
    -2.52
    µ
    -2.34
    ĸ´
    -2.34
    ¦
    -2.31
    ¿
    -2.30
    Ľ
    -2.29
    POSITIVE LOGITS
    anguage
    1.88
    arcelona
    1.85
    abil
    1.81
    ERTY
    1.78
    olutions
    1.74
    ialog
    1.71
    ibil
    1.70
    emin
    1.69
    enda
    1.68
    usiness
    1.65
    Activations Density 5.016%

    No Known Activations