© 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. 25325
    Prev
    Next
    INDEX
    Explanations

    occurrences of the sequence "CHO"

    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
    16
    +0.13
    0.7%
    458
    +0.13
    0.7%
    334
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.13
    0.01
    334
    +0.13
    0.01
    105
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.24
    amyl
    -1.60
    ³
    -1.56
    "}](#
    -1.55
    hib
    -1.50
    ĻĤ
    -1.49
    chten
    -1.49
    ¿½
    -1.44
    hed
    -1.44
    ĨĴ
    -1.43
    POSITIVE LOGITS
    ynom
    1.62
    ERN
    1.61
    IVE
    1.54
    rette
    1.52
     foreseeable
    1.45
    umber
    1.45
    ove
    1.44
    ilo
    1.43
    ’
    1.37
    ÅĽÄĩ
    1.34
    Activations Density 0.013%

    No Known Activations