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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14535
    Prev
    Next
    INDEX
    Explanations

    terms related to immunotherapy and cancer treatment

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.17
    1.0%
    255
    +0.17
    1.0%
    175
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.17
    0.01
    448
    +0.17
    0.01
    255
    +0.11
    0.00
    Negative Logits
    atically
    -1.59
    ually
    -1.42
    ialize
    -1.35
    ubicin
    -1.35
     mine
    -1.35
     count
    -1.35
    irected
    -1.34
     turnout
    -1.33
    ulously
    -1.30
    itatively
    -1.29
    POSITIVE LOGITS
    ²
    5.69
    §
    5.62
    ¼
    5.58
    ¯
    5.44
    ¤
    5.44
    Ĥ
    5.41
    ĸ
    5.37
    ĥ
    5.33
    ·
    5.31
    Ŀ
    5.28
    Activations Density 0.022%

    No Known Activations