© 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. 28566
    Prev
    Next
    INDEX
    Explanations

    technical specifications and parameters related to computing or digital systems

    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
    59
    +0.15
    0.9%
    192
    +0.14
    0.8%
    241
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.15
    -0.00
    59
    +0.14
    0.12
    192
    +0.13
    0.10
    Negative Logits
    ochond
    -1.54
    este
    -1.49
    giving
    -1.43
    hed
    -1.42
    pler
    -1.42
    amer
    -1.31
    áĢº
    -1.30
    ér
    -1.30
    Office
    -1.30
    etting
    -1.28
    POSITIVE LOGITS
    Ļª
    4.93
    ł
    4.88
    ↵        ↵
    4.72
    <|outofrange|>
    4.72
                ↵
    4.72
    4.72
    <|outofrange|>
    4.72
    ↵↵
    4.72
    ↵↵↵
    4.72
    čč
    4.72
    Activations Density 3.098%

    No Known Activations