© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26500
    Prev
    Next
    INDEX
    Explanations

    references to visitor centers or attractions

    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/2-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.2.hook_mlp_out
    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
    233
    +0.11
    0.6%
    323
    +0.11
    0.6%
    375
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.11
    0.09
    232
    +0.11
    0.07
    375
    +0.11
    0.07
    Negative Logits
    ships
    -1.85
    noreply
    -1.63
    essen
    -1.58
    enron
    -1.51
    blogger
    -1.50
     neighbouring
    -1.41
     blockade
    -1.38
    ISPR
    -1.37
    regulation
    -1.37
    icans
    -1.36
    POSITIVE LOGITS
    ield
    1.61
    itness
    1.44
     gravity
    1.42
    lement
    1.34
     Grav
    1.33
    aber
    1.30
    anted
    1.29
    oint
    1.29
    ermine
    1.27
    uration
    1.27
    Activations Density 1.952%

    No Known Activations