© 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 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. 28364
    Prev
    Next
    INDEX
    Explanations

    references to structured data elements or lists

    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
    310
    +0.14
    0.7%
    65
    +0.13
    0.7%
    158
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.14
    0.06
    258
    +0.13
    0.06
    155
    +0.12
    0.05
    Negative Logits
    ľĵ
    -2.45
    ĥ
    -2.35
    ī
    -2.09
    Ī
    -2.03
    £
    -2.01
    ģ
    -1.99
    ¹
    -1.84
    Ħ
    -1.80
    ľ
    -1.79
    ¨
    -1.76
    POSITIVE LOGITS
    eless
    1.66
    iast
    1.49
    arent
    1.47
    (*
    1.45
    liest
    1.42
    ammad
    1.41
    iary
    1.41
    harmonic
    1.40
    amel
    1.39
    ingly
    1.38
    Activations Density 0.060%

    No Known Activations