© 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. 2-MLP-SM
    11. 23401
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presentation and discussion of scientific findings or proposals

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    320
    +0.14
    0.7%
    102
    +0.12
    0.6%
    138
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.14
    0.05
    102
    +0.12
    0.03
    335
    +0.10
    0.06
    Negative Logits
    orously
    -1.82
     )$
    -1.60
    matically
    -1.60
    Ĺ
    -1.59
    ursuant
    -1.54
    µ
    -1.45
     ammon
    -1.45
     okay
    -1.42
    umably
    -1.41
     contrary
    -1.41
    POSITIVE LOGITS
    hood
    1.65
    erton
    1.52
     âĢķ
    1.45
    aching
    1.44
    iera
    1.43
    ÂĴ
    1.43
    ème
    1.43
    ienne
    1.41
    ologie
    1.39
    acher
    1.39
    Activations Density 0.270%

    No Known Activations