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. 2-RES-SM
    6. 29512
    Prev
    Next
    INDEX
    Explanations

    instances of legal terminology and references to court cases

    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
    271
    +0.15
    0.9%
    442
    +0.14
    0.8%
    263
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.15
    -0.01
    431
    +0.14
    0.06
    207
    +0.12
    0.06
    Negative Logits
    :`
    -1.79
    (),
    -1.54
    gage
    -1.52
    ieurs
    -1.38
    issions
    -1.37
     capacities
    -1.35
    reptococcus
    -1.32
     ({
    -1.32
    ÃŃv
    -1.31
    clamation
    -1.30
    POSITIVE LOGITS
    ĻĤ
    1.52
     anytime
    1.45
    east
    1.41
    thing
    1.40
     monks
    1.27
    )\].
    1.26
     knights
    1.25
    acle
    1.24
     dep
    1.19
    instein
    1.19
    Activations Density 2.637%

    No Known Activations