© 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. 28567
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to software development and data management

    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
    422
    +0.15
    0.9%
    34
    +0.13
    0.7%
    261
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.15
    0.14
    422
    +0.13
    0.06
    207
    +0.10
    0.04
    Negative Logits
     tolerated
    -1.48
     tongue
    -1.47
     dam
    -1.43
     remainder
    -1.40
    done
    -1.39
     ground
    -1.38
     rest
    -1.37
    uple
    -1.36
     throat
    -1.34
    orphism
    -1.33
    POSITIVE LOGITS
    ©
    1.60
    ivism
    1.56
    §
    1.51
    ¿½
    1.48
     ÂĹ
    1.47
    ¸
    1.47
    ichte
    1.47
    ¯
    1.47
     —
    1.42
    ibles
    1.42
    Activations Density 3.708%

    No Known Activations