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. 28783
    Prev
    Next
    INDEX
    Explanations

    words related to monitoring and recording activities or data

    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
    +0.15
    0.8%
    404
    +0.10
    0.6%
    298
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.15
    0.01
    115
    +0.10
    0.02
    334
    +0.10
    0.02
    Negative Logits
    Ĺ
    -2.83
    ĥ½
    -2.77
    §
    -2.77
    ĥ
    -2.74
    ĸ´
    -2.65
    «
    -2.60
    Ķ
    -2.52
    ¡
    -2.49
    µ
    -2.49
    ĵ
    -2.44
    POSITIVE LOGITS
    down
    2.49
    ings
    2.21
    backs
    2.11
    ball
    1.95
    age
    1.79
    DOWN
    1.71
     down
    1.70
    ement
    1.70
    sworth
    1.69
    worth
    1.68
    Activations Density 0.127%

    No Known Activations