© 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. 27936
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a request for help or assistance

    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
    197
    +0.16
    0.9%
    455
    +0.13
    0.7%
    302
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.16
    0.06
    302
    +0.13
    0.05
    263
    +0.12
    0.07
    Negative Logits
    idas
    -1.65
     predominantly
    -1.60
     grew
    -1.54
     largely
    -1.54
     governed
    -1.53
     inversely
    -1.53
     territories
    -1.49
     follicular
    -1.47
     multiplied
    -1.46
     fluct
    -1.45
    POSITIVE LOGITS
    éĹ®
    1.70
    ERR
    1.54
    |$.
    1.54
    >>
    1.53
     trouble
    1.50
    ]\\
    1.48
    help
    1.48
    Ignore
    1.47
    IEEE
    1.45
    ]--
    1.44
    Activations Density 0.850%

    No Known Activations