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. 26939
    Prev
    Next
    INDEX
    Explanations

    words related to the influence or impact of various factors on situations or subjects

    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
    156
    +0.21
    1.2%
    23
    +0.18
    1.0%
    376
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.21
    0.01
    277
    +0.18
    0.02
    200
    +0.15
    0.02
    Negative Logits
    clamation
    -1.77
    liche
    -1.72
    sburg
    -1.69
    illac
    -1.64
    illard
    -1.61
    ublic
    -1.60
    gio
    -1.59
    pherd
    -1.56
    CRIPTION
    -1.54
    neys
    -1.52
    POSITIVE LOGITS
    Ļª
    2.39
    ¥
    2.36
    ł
    2.22
    ¶
    2.11
    ©
    2.07
    Ł
    2.07
    Ĩ
    2.04
    ķ
    2.03
    ĺ
    2.01
    ¬
    2.00
    Activations Density 0.098%

    No Known Activations