© 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. 26255
    Prev
    Next
    INDEX
    Explanations

    opening parentheses in the text

    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
    488
    +0.14
    0.8%
    29
    +0.12
    0.6%
    510
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.24
    486
    +0.12
    0.16
    154
    +0.11
    0.15
    Negative Logits
    cloth
    -1.47
    reve
    -1.43
    eligible
    -1.40
    bone
    -1.38
    blockList
    -1.37
    mog
    -1.35
    +$
    -1.35
     oxidase
    -1.34
    plements
    -1.34
    etc
    -1.34
    POSITIVE LOGITS
    ²
    3.02
    Ń
    3.02
    µ
    2.98
    İ
    2.81
    ĩ
    2.79
    ħ
    2.79
    Ĭ
    2.76
    ¡
    2.75
    ©
    2.74
    ³
    2.73
    Activations Density 0.344%

    No Known Activations