© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 29699
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court cases

    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
    111
    +0.16
    1.0%
    271
    +0.14
    0.8%
    326
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.16
    0.02
    386
    +0.14
    0.01
    270
    +0.13
    0.02
    Negative Logits
    cgi
    -1.71
    XM
    -1.57
     HS
    -1.57
     AH
    -1.46
     NZ
    -1.43
     Information
    -1.42
     Nucle
    -1.42
     HR
    -1.38
     HM
    -1.35
     CCT
    -1.34
    POSITIVE LOGITS
    ŀ
    2.22
    Ĵ
    2.01
    Ĥ¬
    1.96
    »¿
    1.93
    ©
    1.88
    °
    1.88
    Ļª
    1.88
    ½
    1.87
    ¤
    1.85
    Ī
    1.79
    Activations Density 0.134%

    No Known Activations