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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12190
    Prev
    Next
    INDEX
    Explanations

    expressions indicating perception or opinion

    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
    335
    +0.14
    0.8%
    376
    +0.12
    0.7%
    144
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.04
    390
    +0.12
    0.02
    144
    +0.11
    0.02
    Negative Logits
    §
    -3.63
    ¸
    -3.51
    ĭ
    -3.32
    Ģ
    -3.28
    ĥ
    -3.15
    ª
    -3.14
    ļ
    -3.13
    IJ
    -3.13
    į
    -3.08
    ģ
    -3.04
    POSITIVE LOGITS
    ifiable
    1.66
    int
    1.64
    DTD
    1.62
     0000000000000000000000000000000000
    1.60
     hopeless
    1.54
    ly
    1.52
    ulous
    1.51
    ylum
    1.50
    ivalence
    1.49
    eless
    1.44
    Activations Density 0.155%

    No Known Activations