© 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. Residuals
    9. 1-RES-SM
    11. 29533
    Prev
    Next
    INDEX
    Explanations

    the verb "am" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    396
    +0.14
    0.8%
    74
    +0.12
    0.7%
    356
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.14
    0.03
    74
    +0.12
    0.03
    405
    +0.12
    0.03
    Negative Logits
    ±
    -3.56
    ĵ
    -3.38
    ķ
    -3.35
    ĥ
    -3.16
    £
    -3.10
    Ĺ
    -3.08
    Ĩ
    -3.08
    Ķ
    -3.05
    Ń
    -3.04
    ¥
    -3.01
    POSITIVE LOGITS
    orphous
    2.08
    oxifen
    1.94
    plitudes
    1.93
    eless
    1.91
    irez
    1.86
    endi
    1.84
    sterdam
    1.82
    endment
    1.82
    istic
    1.80
    andi
    1.74
    Activations Density 0.091%

    No Known Activations