© 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. 4696
    Prev
    Next
    INDEX
    Explanations

    terminology related to astrophysics and scientific concepts

    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
    314
    +0.13
    0.6%
    389
    +0.09
    0.4%
    155
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    0.01
    701
    +0.09
    0.05
    232
    +0.09
    0.07
    Negative Logits
    hare
    -0.76
    Saharan
    -0.62
    pend
    -0.59
    bors
    -0.59
    ld
    -0.58
    unin
    -0.58
    regate
    -0.58
     starters
    -0.58
     laun
    -0.57
    gg
    -0.56
    POSITIVE LOGITS
    icians
    1.35
    ically
    1.22
    ics
    1.22
    ician
    1.21
    ical
    1.21
    osis
    1.17
    icism
    1.17
    ICAL
    1.15
    ique
    1.14
    icist
    1.13
    Activations Density 1.060%

    No Known Activations