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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-SM
    6. 29201
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or critiques

    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
    249
    +0.18
    1.1%
    203
    +0.15
    0.8%
    97
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.18
    0.07
    97
    +0.15
    0.07
    203
    +0.14
    0.07
    Negative Logits
    -"
    -1.78
    atically
    -1.62
    orect
    -1.57
    OOGLE
    -1.54
    eful
    -1.49
     "./
    -1.49
    ributes
    -1.47
    ensitive
    -1.45
     "/
    -1.45
    umns
    -1.42
    POSITIVE LOGITS
    ¾
    1.99
    ©
    1.88
    ī
    1.84
    ·
    1.80
    ish
    1.78
    Ĥ
    1.73
    ¯
    1.71
    ®
    1.69
    heit
    1.60
    ¶
    1.57
    Activations Density 0.218%

    No Known Activations