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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29765
    Prev
    Next
    INDEX
    Explanations

    words related to various types of vehicles

    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
    156
    +0.24
    1.4%
    358
    +0.14
    0.8%
    150
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.24
    0.03
    93
    +0.14
    0.04
    189
    +0.14
    0.03
    Negative Logits
    ĥ½
    -2.45
    ĥ
    -2.13
    £
    -2.02
     hope
    -1.93
    Ĥ¬
    -1.80
    Ŀ
    -1.76
    ermost
    -1.74
     theolog
    -1.72
    ·
    -1.72
    «
    -1.66
    POSITIVE LOGITS
    ousel
    2.70
    illon
    2.04
    nel
    1.85
    "}](#
    1.78
    wheel
    1.71
    pow
    1.64
    avan
    1.63
    park
    1.61
    gun
    1.60
    ines
    1.60
    Activations Density 0.166%

    No Known Activations