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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11986
    Prev
    Next
    INDEX
    Explanations

    references to land and property ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    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
    +0.14
    0.8%
    248
    +0.11
    0.6%
    507
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.14
    0.02
    46
    +0.11
    0.01
    181
    +0.11
    0.02
    Negative Logits
    Ĥ
    -1.91
    Ń
    -1.90
    Ŀ
    -1.75
    ľĵ
    -1.74
    Į
    -1.64
    ¡
    -1.59
     vaginal
    -1.58
    ³
    -1.55
    «
    -1.52
    ·
    -1.51
    POSITIVE LOGITS
    owner
    2.24
    owners
    2.21
    lords
    2.18
    estine
    2.15
    INGS
    2.01
    fill
    1.96
    ings
    1.96
    locked
    1.96
    scape
    1.95
    holder
    1.75
    Activations Density 0.161%

    No Known Activations