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. MLP Post
    5. 0-MLP-SM
    6. 27469
    Prev
    Next
    INDEX
    Explanations

    mentions of "basket" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.20
    1.2%
    125
    +0.11
    0.7%
    465
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    465
    +0.20
    0.01
    401
    +0.11
    0.01
    319
    +0.10
    0.01
    Negative Logits
     yours
    -1.74
     vain
    -1.53
     Hour
    -1.47
     Walt
    -1.44
     Skype
    -1.44
     anybody
    -1.43
     Publ
    -1.41
     myself
    -1.40
     their
    -1.39
     everyone
    -1.38
    POSITIVE LOGITS
    ĻĤ
    2.15
    Ŀ
    2.09
    į
    2.04
    ģ
    1.89
    ¼
    1.83
    makers
    1.82
    ľ
    1.79
    holder
    1.76
    iff
    1.74
    amental
    1.74
    Activations Density 0.019%

    No Known Activations