© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27974
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to surfaces

    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
    156
    +0.16
    0.9%
    256
    +0.14
    0.8%
    219
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    256
    +0.16
    0.02
    219
    +0.14
    0.02
    287
    +0.14
    0.02
    Negative Logits
    grily
    -1.68
    ish
    -1.59
    severe
    -1.59
    sell
    -1.57
    §
    -1.47
    ĥ½
    -1.46
     antidepress
    -1.43
    Į
    -1.43
    son
    -1.42
     frequent
    -1.42
    POSITIVE LOGITS
    plate
    2.09
    plates
    2.02
    "}](#
    2.00
    borne
    1.86
    criptor
    1.77
    ]:
    1.71
    ahead
    1.70
    oft
    1.64
    cloth
    1.59
    imetry
    1.58
    Activations Density 0.064%

    No Known Activations