© 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. 28569
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate change or transformation

    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
    358
    +0.14
    0.8%
    470
    +0.13
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.14
    0.04
    62
    +0.13
    0.03
    196
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -3.10
    ¿
    -2.76
    Ļ
    -2.58
    į
    -2.57
    ĥ
    -2.55
    ľĵ
    -2.45
    Īĺ
    -2.38
    ©
    -2.35
    ľ
    -2.34
    ĺ
    -2.31
    POSITIVE LOGITS
    tons
    1.70
     routines
    1.65
     matters
    1.52
     regimes
    1.48
     wording
    1.47
     behaviour
    1.46
     habits
    1.41
     gears
    1.40
    pone
    1.40
    verted
    1.40
    Activations Density 0.159%

    No Known Activations