© 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. 8-RES_POST_32K-OAI
    11. 5879
    Prev
    Next
    INDEX
    Explanations

    terms related to enhancement or improving processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    297
    +0.12
    0.5%
    723
    +0.10
    0.5%
    553
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.12
    0.01
    348
    +0.10
    0.01
    165
    +0.10
    0.00
    Negative Logits
     tremend
    -0.79
     cohesion
    -0.70
     glac
    -0.69
    eus
    -0.66
     postage
    -0.66
     loyalty
    -0.65
     stiffness
    -0.64
     Pyth
    -0.64
     Citadel
    -0.64
     Celest
    -0.64
    POSITIVE LOGITS
    Zip
    0.79
    enough
    0.79
    estyle
    0.76
    yright
    0.75
    Delete
    0.70
    generated
    0.70
    ãĤµ
    0.69
    tm
    0.69
    lasses
    0.68
    iku
    0.67
    Activations Density 0.025%

    No Known Activations