© 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. 29783
    Prev
    Next
    INDEX
    Explanations

    words suggesting being without support or stability

    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
    376
    +0.16
    0.9%
    377
    +0.15
    0.8%
    118
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.16
    0.02
    384
    +0.15
    0.01
    274
    +0.14
    0.01
    Negative Logits
    lessness
    -1.95
    unnumbered
    -1.47
    fulness
    -1.44
    inian
    -1.43
    lessly
    -1.38
     sido
    -1.37
    isme
    -1.35
    isy
    -1.35
    ise
    -1.32
    ulence
    -1.30
    POSITIVE LOGITS
    ĻĤ
    3.49
    Ģ
    3.00
    ³
    2.90
    ģ
    2.72
    Ĩ
    2.67
    ·¸
    2.62
    Ļ
    2.61
    ij
    2.56
    ł
    2.56
    Ĵ
    2.48
    Activations Density 0.067%

    No Known Activations