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. 27646
    Prev
    Next
    INDEX
    Explanations

    mentions of land or property, particularly referring to tracts or parcels

    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
    148
    +0.13
    0.7%
    43
    +0.13
    0.7%
    125
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.13
    0.01
    43
    +0.13
    0.01
    125
    +0.12
    0.01
    Negative Logits
     sexes
    -1.66
    semin
    -1.59
     lifetime
    -1.52
     sex
    -1.49
     promise
    -1.47
    then
    -1.45
     tear
    -1.45
     separate
    -1.42
     departure
    -1.41
    alen
    -1.40
    POSITIVE LOGITS
    ©
    2.10
    ĻĤ
    2.06
    ĸ
    2.02
    ¿½
    2.02
    ľ
    1.98
    į
    1.87
    Ķ
    1.87
    »¿
    1.86
    ģ
    1.83
    °
    1.74
    Activations Density 0.200%

    No Known Activations