© 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. 29781
    Prev
    Next
    INDEX
    Explanations

    adjectives with the suffix 'ous' and their variations

    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
    314
    +0.13
    0.6%
    304
    +0.13
    0.6%
    241
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.03
    314
    +0.13
    -0.00
    284
    +0.11
    0.02
    Negative Logits
     EDITION
    -0.67
     parentheses
    -0.64
     opposite
    -0.60
     ANG
    -0.58
     foreign
    -0.58
     Zo
    -0.58
     Lann
    -0.58
     Downs
    -0.57
    VALUE
    -0.57
     antit
    -0.57
    POSITIVE LOGITS
    say
    1.17
    sa
    1.10
    sin
    1.10
    si
    1.07
    hiro
    1.02
    sac
    1.01
    hey
    1.01
    hi
    1.01
    san
    0.98
    sim
    0.98
    Activations Density 0.205%

    No Known Activations