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. 28985
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to algorithms or mathematical expressions

    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
    369
    +0.18
    1.0%
    320
    +0.13
    0.7%
    382
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.18
    0.00
    436
    +0.13
    0.03
    369
    +0.13
    0.01
    Negative Logits
    )\].
    -1.87
    )</
    -1.80
    )\]
    -1.74
    ):
    -1.59
    }</
    -1.59
    ));
    -1.58
     none
    -1.54
    )];
    -1.54
    ");
    -1.53
    )):
    -1.52
    POSITIVE LOGITS
    dern
    1.64
    ,\,
    1.50
     heels
    1.49
    ammat
    1.46
    due
    1.44
     inflation
    1.42
    »
    1.41
    iff
    1.40
    iale
    1.39
    amsbsy
    1.38
    Activations Density 0.156%

    No Known Activations