© 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. 28538
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to software usage and licensing

    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
    205
    +0.14
    0.8%
    2
    +0.13
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.14
    0.02
    205
    +0.13
    0.01
    268
    +0.12
    0.01
    Negative Logits
    Īĺ
    -3.23
    ľĵ
    -3.21
    ĨĴ
    -3.19
    ĸ
    -3.13
    ¦
    -3.11
    ı
    -3.10
    ®
    -3.07
    ¡
    -3.05
    ¿½
    -3.02
    İ
    -3.00
    POSITIVE LOGITS
     imposed
    1.75
     breach
    1.55
    ↵
    1.51
     overr
    1.51
     Âĵ
    1.49
     implied
    1.49
     condition
    1.46
     invalid
    1.42
     conditions
    1.42
     effect
    1.41
    Activations Density 0.048%

    No Known Activations