© 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. 23154
    Prev
    Next
    INDEX
    Explanations

    contrasting statements or transitions in the text

    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
    58
    +0.13
    0.7%
    366
    +0.12
    0.6%
    165
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.13
    0.00
    255
    +0.12
    0.00
    466
    +0.11
    0.00
    Negative Logits
    ¿½
    -1.91
    fte
    -1.82
    ellar
    -1.66
    oslav
    -1.44
    back
    -1.44
    eps
    -1.41
    heta
    -1.41
    hered
    -1.41
    ://
    -1.39
    ceral
    -1.39
    POSITIVE LOGITS
    ances
    1.71
    ieurs
    1.54
     Animals
    1.40
     animal
    1.40
     electrical
    1.38
    itudes
    1.37
    ance
    1.36
     contractor
    1.36
    vity
    1.30
     invisible
    1.30
    Activations Density 0.000%

    No Known Activations