© 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. 29573
    Prev
    Next
    INDEX
    Explanations

    the word "feature" 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
    24
    +0.12
    0.6%
    365
    +0.11
    0.6%
    277
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    473
    +0.12
    0.02
    92
    +0.11
    0.02
    289
    +0.10
    0.02
    Negative Logits
    =`
    -1.70
    ):
    -1.69
    rieve
    -1.67
    irds
    -1.49
    rants
    -1.46
    heed
    -1.45
    uuid
    -1.44
    tags
    -1.42
    '):
    -1.40
    IONS
    -1.39
    POSITIVE LOGITS
    ĥ
    1.45
    jem
    1.43
    ĵ
    1.42
     permit
    1.34
    itrile
    1.33
     whole
    1.32
     matter
    1.32
     agenda
    1.30
     masses
    1.29
    ¸
    1.29
    Activations Density 0.007%

    No Known Activations