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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30231
    Prev
    Next
    INDEX
    Explanations

    references to different categories or classifications

    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
    268
    +0.13
    0.7%
    169
    +0.13
    0.7%
    197
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.13
    0.03
    116
    +0.13
    0.02
    285
    +0.13
    0.03
    Negative Logits
    ĻĤ
    -3.17
    ±
    -2.44
    ľĵ
    -2.39
    ©
    -2.23
    §
    -1.86
    ĥ
    -1.85
    ĸ´
    -1.82
    InstanceState
    -1.82
    ¦
    -1.81
    ¡
    -1.73
    POSITIVE LOGITS
    cript
    2.65
    etting
    2.46
    faces
    2.06
    oss
    1.75
    paces
    1.70
    ert
    1.69
    ports
    1.68
    ahead
    1.64
    mith
    1.64
    eller
    1.60
    Activations Density 0.073%

    No Known Activations