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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 26862
    Prev
    Next
    INDEX
    Explanations

    words related to technology and electronic devices

    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
    208
    +0.12
    0.7%
    503
    +0.12
    0.7%
    488
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.12
    0.01
    503
    +0.12
    0.01
    300
    +0.12
    0.02
    Negative Logits
     gonna
    -1.73
    STRA
    -1.59
     distant
    -1.58
     toast
    -1.57
     careful
    -1.53
     pure
    -1.51
    Âł↵
    -1.49
     substantial
    -1.49
     formal
    -1.46
     sincere
    -1.44
    POSITIVE LOGITS
    £
    3.44
    º
    3.32
    ¢
    3.31
    IJ
    3.24
    ¯
    3.21
    ĻĤ
    3.19
    ³
    3.16
    ĩ
    3.13
    Ł
    3.08
    ¼
    3.06
    Activations Density 0.097%

    No Known Activations