© 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. 29399
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions that indicate speech or thought

    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
    +0.15
    0.9%
    334
    +0.15
    0.9%
    107
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.15
    0.01
    107
    +0.15
    0.01
    260
    +0.12
    0.01
    Negative Logits
    ĵ
    -3.88
    ·¸
    -3.62
    ¤
    -3.48
    »
    -3.18
    ī
    -3.18
    ĭ
    -3.17
    ij
    -3.13
    ¬
    -3.07
    ¦
    -3.02
    ĻĤ
    -2.91
    POSITIVE LOGITS
    rooms
    2.02
    room
    2.01
    ings
    1.92
    aways
    1.92
    ional
    1.75
    doll
    1.67
     toll
    1.60
    idable
    1.59
    gres
    1.51
    jä
    1.49
    Activations Density 0.022%

    No Known Activations