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. 26819
    Prev
    Next
    INDEX
    Explanations

    words related to entitlement or privileges

    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
    203
    +0.18
    1.0%
    410
    +0.14
    0.8%
    470
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.18
    0.02
    283
    +0.14
    0.02
    470
    +0.11
    0.01
    Negative Logits
    poons
    -1.94
    backs
    -1.67
    unnable
    -1.61
    ontal
    -1.47
     throat
    -1.45
    quin
    -1.42
     else
    -1.42
    fully
    -1.40
    put
    -1.39
    xit
    -1.39
    POSITIVE LOGITS
    ourage
    1.87
    Ŀ
    1.76
    ele
    1.53
    rants
    1.51
    ibase
    1.49
    angle
    1.46
    transcript
    1.42
    iendo
    1.39
     bloc
    1.38
    array
    1.38
    Activations Density 0.080%

    No Known Activations