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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 27280
    Prev
    Next
    INDEX
    Explanations

    numerical values or counts

    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
    69
    +0.15
    0.8%
    81
    +0.13
    0.8%
    458
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.15
    0.04
    241
    +0.13
    0.04
    458
    +0.13
    0.04
    Negative Logits
     yours
    -1.62
    ?).
    -1.52
    ity
    -1.48
    ...](
    -1.46
    onia
    -1.44
     late
    -1.42
    thon
    -1.41
     nobody
    -1.41
    haps
    -1.40
    OutputStream
    -1.37
    POSITIVE LOGITS
    bed
    1.58
    itars
    1.47
    teenth
    1.42
    ycin
    1.40
    zerba
    1.40
    ele
    1.38
    abad
    1.37
    cale
    1.37
    iate
    1.33
    ultan
    1.32
    Activations Density 0.031%

    No Known Activations