© 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. 25464
    Prev
    Next
    INDEX
    Explanations

    occurrences of "VERSION 10"

    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
    351
    +0.14
    0.9%
    202
    +0.13
    0.8%
    397
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.14
    0.02
    351
    +0.13
    0.02
    397
    +0.13
    0.01
    Negative Logits
     away
    -1.87
     pity
    -1.74
     welcome
    -1.70
     suspected
    -1.67
     distance
    -1.64
     guilt
    -1.60
     noticed
    -1.58
    )^{-
    -1.58
     mercy
    -1.57
     somebody
    -1.57
    POSITIVE LOGITS
    etica
    2.08
    etable
    1.93
    Ŀ
    1.82
    anguage
    1.77
    º
    1.76
    aic
    1.75
    ariate
    1.74
    sheet
    1.72
    İ
    1.71
    ĻĤ
    1.70
    Activations Density 0.014%

    No Known Activations