Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28939
    Prev
    Next
    INDEX
    Explanations

    items related to visual formatting specifications

    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
    225
    +0.15
    0.8%
    354
    +0.12
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.15
    0.03
    410
    +0.12
    0.04
    82
    +0.12
    0.03
    Negative Logits
    oarthritis
    -1.68
    izable
    -1.51
    prise
    -1.49
    puted
    -1.48
    ês
    -1.48
     realise
    -1.43
     realize
    -1.40
    prises
    -1.39
    ·¸
    -1.35
    escence
    -1.34
    POSITIVE LOGITS
    appa
    2.10
    linger
    1.88
    ings
    1.74
    inger
    1.67
    gart
    1.66
    ringer
    1.59
    lers
    1.59
    ling
    1.55
    lem
    1.53
    tk
    1.53
    Activations Density 0.322%

    No Known Activations