© 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. 29599
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'f'

    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
    412
    +0.12
    0.6%
    369
    +0.12
    0.6%
    189
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.12
    0.05
    189
    +0.12
    0.05
    209
    +0.11
    0.05
    Negative Logits
    ĨĴ
    -2.25
    º
    -2.13
    ±
    -2.07
    ¢
    -2.01
    ·¸
    -2.00
    »¿
    -2.00
    ĸ´
    -1.99
    ¼
    -1.85
    Ĥ
    -1.84
    °
    -1.83
    POSITIVE LOGITS
    arts
    1.73
    aux
    1.66
    inally
    1.65
    licts
    1.64
    work
    1.62
    rees
    1.59
    alt
    1.59
    erguson
    1.57
    lic
    1.52
    doibase
    1.51
    Activations Density 0.663%

    No Known Activations