© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28713
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronics and power systems

    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
    198
    +0.21
    1.2%
    263
    +0.20
    1.2%
    169
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.21
    0.16
    263
    +0.20
    0.16
    204
    +0.18
    0.13
    Negative Logits
    ¯
    -1.49
    °
    -1.40
     age
    -1.40
    orum
    -1.39
    cker
    -1.39
    ilt
    -1.37
     moot
    -1.36
     coron
    -1.35
    pora
    -1.33
    ¸
    -1.32
    POSITIVE LOGITS
    )$)
    1.55
    ...]
    1.54
     wonders
    1.44
    substack
    1.40
    usions
    1.40
    ![(
    1.35
    Things
    1.35
    msgstr
    1.34
    ,...
    1.33
    leftarrow
    1.33
    Activations Density 4.214%

    No Known Activations