Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11490
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and queries

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    360
    +0.11
    0.6%
    125
    +0.11
    0.6%
    79
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.11
    0.01
    55
    +0.11
    0.02
    360
    +0.10
    0.01
    Negative Logits
    msgstr
    -1.62
    aspx
    -1.60
    <
    -1.53
     BGCOLOR
    -1.44
    .</
    -1.40
    awning
    -1.39
    ]>
    -1.39
    >/
    -1.38
    [^
    -1.35
    red
    -1.34
    POSITIVE LOGITS
    icians
    1.58
     pylori
    1.54
     prob
    1.44
    ils
    1.32
     meant
    1.30
    enos
    1.28
    etes
    1.27
    ician
    1.25
    jon
    1.22
     Brothers
    1.22
    Activations Density 0.088%

    No Known Activations