© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26992
    Prev
    Next
    INDEX
    Explanations

    references to places providing shelter

    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
    115
    +0.15
    0.9%
    376
    +0.12
    0.7%
    470
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.15
    0.01
    360
    +0.12
    0.01
    453
    +0.12
    0.01
    Negative Logits
    ĥ
    -2.38
    ¯
    -1.93
    §
    -1.91
    ı
    -1.85
    ¿
    -1.80
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.79
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.75
    ²
    -1.74
    ¬
    -1.72
    ĥ½
    -1.71
    POSITIVE LOGITS
    holder
    1.89
    inson
    1.70
    plate
    1.64
    piece
    1.60
    plant
    1.55
    fors
    1.53
    ilated
    1.53
    belt
    1.51
    igraph
    1.49
    ÃŃo
    1.48
    Activations Density 0.036%

    No Known Activations