© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29280
    Prev
    Next
    INDEX
    Explanations

    modifiers or adjectives that describe quantity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    729
    +0.13
    0.6%
    540
    +0.10
    0.5%
    747
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.13
    0.12
    250
    +0.10
    0.06
    159
    +0.10
    0.06
    Negative Logits
    die
    -0.67
    udeb
    -0.66
    20439
    -0.64
    UGC
    -0.60
    dit
    -0.60
    effects
    -0.58
    idas
    -0.58
    aman
    -0.58
    ividual
    -0.58
     Daylight
    -0.58
    POSITIVE LOGITS
     exaggeration
    1.08
     understatement
    1.04
     stretch
    0.92
     awfully
    0.90
     dubious
    0.86
     lofty
    0.85
     overs
    0.84
     tall
    0.84
     feat
    0.83
    bold
    0.82
    Activations Density 0.768%

    No Known Activations