© 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. 25057
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols, indicating a focus on sentence structure and breaks

    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
    195
    +0.18
    1.0%
    283
    +0.10
    0.6%
    350
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.09
    17
    +0.10
    0.03
    271
    +0.10
    0.01
    Negative Logits
    ([]
    -1.53
    ('/
    -1.53
    Formatter
    -1.47
    caster
    -1.44
     tweets
    -1.41
    WITH
    -1.34
    ")]
    -1.34
    posts
    -1.34
    Fish
    -1.33
    ("/
    -1.33
    POSITIVE LOGITS
    §
    3.65
    ½
    3.59
    ģ
    3.51
    ¡
    3.41
    ŀ
    3.38
    č↵
    3.37
    <|outofrange|>
    3.37
    ↵
    3.37
    ↵  ↵
    3.37
    <|outofrange|>
    3.37
    Activations Density 0.604%

    No Known Activations