© 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. 26462
    Prev
    Next
    INDEX
    Explanations

    information related to cancer treatment and clinical trials

    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
    156
    +0.23
    1.3%
    29
    +0.12
    0.7%
    294
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.23
    0.07
    277
    +0.12
    0.06
    294
    +0.11
    0.05
    Negative Logits
    ł
    -3.26
    £
    -3.01
    Ĺ
    -2.84
    Ł
    -2.75
    ĻĤ
    -2.74
    ľĵ
    -2.70
    ķ
    -2.70
    ĺ
    -2.65
    ³
    -2.61
    ŀ
    -2.61
    POSITIVE LOGITS
    atories
    1.47
     Wa
    1.47
    izens
    1.42
    ('',
    1.40
    framework
    1.38
     rebuilt
    1.37
     vacated
    1.37
     Commerce
    1.37
    schemas
    1.36
     predecessor
    1.36
    Activations Density 0.598%

    No Known Activations