© 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. 2-RES-SM
    11. 13909
    Prev
    Next
    INDEX
    Explanations

    terms related to addiction treatment and support options

    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
    186
    +0.32
    1.9%
    153
    +0.19
    1.1%
    285
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.32
    0.11
    285
    +0.19
    0.16
    153
    +0.17
    0.07
    Negative Logits
     Netanyahu
    -1.39
    </
    -1.38
     lately
    -1.37
     ahead
    -1.32
     feature
    -1.28
    **,
    -1.27
    ooth
    -1.27
    :</
    -1.26
     </
    -1.26
     snaps
    -1.25
    POSITIVE LOGITS
    irst
    1.70
     quo
    1.69
    autres
    1.61
    áĢº
    1.40
    laws
    1.33
    à¹ī
    1.29
    ancial
    1.29
    ÏīÏĤ
    1.25
    quo
    1.25
    ]'
    1.24
    Activations Density 5.013%

    No Known Activations