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

    Neuronpedia

    Jacobian LensNEW
    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. 6717
    Prev
    Next
    INDEX
    Explanations

    topics related to gender identity and the rights of transgender individuals

    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
    125
    +0.13
    0.6%
    439
    +0.10
    0.5%
    643
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.13
    0.05
    235
    +0.10
    0.06
    439
    +0.10
    0.04
    Negative Logits
     Cheap
    -0.79
     Winc
    -0.77
     Roose
    -0.74
    Luck
    -0.73
    assic
    -0.70
    Money
    -0.69
    baugh
    -0.69
     kitchens
    -0.66
     Lever
    -0.66
     Appl
    -0.66
    POSITIVE LOGITS
     genital
    1.08
     dysph
    1.07
     pronouns
    1.05
     Transgender
    1.03
     genders
    1.02
     transsexual
    1.00
     disorder
    0.99
     transgender
    0.99
     chromosomes
    0.98
     biologically
    0.96
    Activations Density 1.111%

    No Known Activations