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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27012
    Prev
    Next
    INDEX
    Explanations

    specific attributes or qualities associated with objects and actions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.33
    1.9%
    23
    +0.19
    1.1%
    271
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.33
    0.17
    271
    +0.19
    -0.06
    116
    +0.15
    0.09
    Negative Logits
     jan
    -1.43
     Rptr
    -1.41
     Ct
    -1.39
    emente
    -1.39
    izione
    -1.36
    ei
    -1.34
     si
    -1.32
    amente
    -1.30
     siRNA
    -1.29
    kowski
    -1.29
    POSITIVE LOGITS
    ·
    2.20
    ľ
    2.11
    Ĺ
    2.07
    İ
    1.93
    µ
    1.92
    ²
    1.84
    IJ
    1.84
    ħ
    1.83
    ij
    1.81
    Īĺ
    1.81
    Activations Density 4.553%

    No Known Activations