Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27065
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific factors or entities, particularly in the context of discussions about environmental issues

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    369
    +0.32
    1.9%
    503
    +0.12
    0.7%
    25
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.32
    0.05
    364
    +0.12
    0.04
    503
    +0.11
    0.04
    Negative Logits
    aign
    -1.74
    iento
    -1.66
    panic
    -1.57
    leans
    -1.52
    idone
    -1.51
    angs
    -1.50
    ère
    -1.48
     ""
    -1.47
     rise
    -1.47
    ations
    -1.46
    POSITIVE LOGITS
    ķ
    1.60
    LECT
    1.58
    TA
    1.55
    ukary
    1.55
    PI
    1.50
    :**
    1.47
    nerg
    1.46
    ):
    1.45
    SI
    1.45
    rika
    1.44
    Activations Density 0.106%

    No Known Activations