© 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. 12274
    Prev
    Next
    INDEX
    Explanations

    blocks of license or copyright information

    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
    224
    +0.15
    0.8%
    146
    +0.12
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.15
    0.02
    222
    +0.12
    0.01
    315
    +0.12
    0.01
    Negative Logits
     science
    -1.45
     distinction
    -1.44
    ...](
    -1.44
    ished
    -1.41
    NEY
    -1.39
    isation
    -1.34
    ently
    -1.34
    pub
    -1.34
    AFFIRMED
    -1.33
    upon
    -1.31
    POSITIVE LOGITS
    ĨĴ
    1.94
    Ļª
    1.92
    µ
    1.74
    ¢
    1.65
    £
    1.52
    Ĥ¬
    1.49
    chitz
    1.47
    §
    1.44
    ª
    1.41
    θ
    1.36
    Activations Density 0.076%

    No Known Activations