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. 29261
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic engineering and biotechnological methods

    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
    156
    +0.23
    1.3%
    29
    +0.13
    0.7%
    472
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.23
    0.01
    29
    +0.13
    0.01
    448
    +0.13
    0.01
    Negative Logits
    omitempty
    -1.68
    continue
    -1.65
     examiner
    -1.57
    tty
    -1.53
    oner
    -1.49
    GLIGENCE
    -1.49
     0000000000000000000000000000000000
    -1.45
     curiam
    -1.43
    CUSS
    -1.43
    olen
    -1.42
    POSITIVE LOGITS
    ł
    3.44
    ±
    3.18
    £
    3.13
    ĸ
    3.07
    ¦
    3.05
    ķ
    3.00
    ĸ´
    2.99
    ¤
    2.99
    ·¸
    2.94
    <|outofrange|>
    2.91
    Activations Density 0.088%

    No Known Activations