© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29679
    Prev
    Next
    INDEX
    Explanations

    terms related to temporary and permanent benefits or statuses in disability and employment contexts

    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
    484
    +0.15
    0.9%
    240
    +0.13
    0.7%
    391
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.15
    0.09
    421
    +0.13
    0.07
    156
    +0.11
    0.12
    Negative Logits
    ‘
    -1.41
     violated
    -1.39
     restored
    -1.36
    alc
    -1.36
    ician
    -1.33
    ../../
    -1.31
    )$-
    -1.30
    ionic
    -1.30
     aroused
    -1.30
     convenient
    -1.29
    POSITIVE LOGITS
    ness
    2.01
     degrees
    1.77
    nier
    1.68
    erals
    1.68
    tees
    1.59
    soever
    1.56
    thirds
    1.55
    ĻĤ
    1.53
    keit
    1.51
    ity
    1.50
    Activations Density 1.577%

    No Known Activations