© 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. 25926
    Prev
    Next
    INDEX
    Explanations

    references to specific rooms or areas

    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
    480
    +0.15
    0.9%
    164
    +0.14
    0.8%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.15
    0.05
    302
    +0.14
    0.03
    168
    +0.12
    0.03
    Negative Logits
    yline
    -1.65
     tear
    -1.47
    еÐ
    -1.45
     precious
    -1.44
     sed
    -1.42
     child
    -1.41
    ureus
    -1.38
     Somerset
    -1.38
    udson
    -1.37
     Snow
    -1.36
    POSITIVE LOGITS
    ingly
    1.82
    ful
    1.78
    mate
    1.77
    ing
    1.75
    istically
    1.73
    ichlet
    1.68
    esy
    1.67
    nal
    1.66
    tables
    1.64
    borne
    1.62
    Activations Density 0.033%

    No Known Activations