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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 11418
    Prev
    Next
    INDEX
    Explanations

    the verb "come" in various contexts and forms

    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
    77
    +0.13
    0.7%
    289
    +0.11
    0.6%
    164
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.13
    0.03
    289
    +0.11
    0.03
    164
    +0.11
    0.04
    Negative Logits
    ĻĤ
    -3.58
    »¿
    -3.55
    Į
    -3.46
    ¢
    -3.41
    ³
    -3.40
    £
    -3.35
    Ń
    -3.29
    į
    -3.28
    §
    -3.23
    ·¸
    -3.14
    POSITIVE LOGITS
     forth
    1.81
    ppo
    1.76
    backs
    1.66
    back
    1.65
     back
    1.58
    oti
    1.57
     hither
    1.55
     prima
    1.55
     vez
    1.51
    ographically
    1.51
    Activations Density 0.214%

    No Known Activations