© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11618
    Prev
    Next
    INDEX
    Explanations

    concepts related to foundational elements and criteria 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    25
    +0.17
    0.9%
    397
    +0.11
    0.6%
    500
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.17
    0.06
    500
    +0.11
    0.07
    462
    +0.10
    0.06
    Negative Logits
    Ĥ
    -5.66
    ¡
    -5.64
    §
    -5.50
    ª
    -5.48
    ½
    -5.36
    Ĵ
    -5.36
    Ĭ
    -5.35
    ¿
    -5.34
    <|outofrange|>
    -5.34
    ↵↵               
    -5.34
    POSITIVE LOGITS
    arity
    2.30
     for
    2.01
    paces
    1.84
    piece
    1.80
    posts
    1.77
    keeping
    1.76
    pace
    1.74
     characterizing
    1.69
     namely
    1.68
    ivism
    1.65
    Activations Density 1.381%

    No Known Activations