© 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. 25606
    Prev
    Next
    INDEX
    Explanations

    the act of searching for something

    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
    376
    +0.16
    0.9%
    148
    +0.12
    0.7%
    173
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.16
    0.02
    45
    +0.12
    0.01
    259
    +0.12
    0.01
    Negative Logits
    jours
    -1.71
    chers
    -1.58
    ching
    -1.51
    hers
    -1.47
    ars
    -1.45
    ás
    -1.38
     fun
    -1.37
    §
    -1.36
    itsu
    -1.36
    devel
    -1.35
    POSITIVE LOGITS
    lessly
    1.53
    ely
    1.50
     aisle
    1.50
     instrument
    1.47
     retard
    1.47
    dal
    1.46
    ressive
    1.45
     pose
    1.44
     behaviours
    1.41
     behaviour
    1.41
    Activations Density 0.026%

    No Known Activations