© 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. 4629
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of masculinity and its representations

    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
    218
    +0.12
    0.6%
    167
    +0.12
    0.5%
    127
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.03
    251
    +0.12
    0.02
    343
    +0.10
    0.02
    Negative Logits
    cycles
    -0.70
    WAYS
    -0.66
    bush
    -0.63
    course
    -0.63
    Medium
    -0.63
     Orbit
    -0.59
     Manz
    -0.58
    LESS
    -0.58
    Grad
    -0.57
     cycles
    -0.57
    POSITIVE LOGITS
    ial
    0.97
    iaries
    0.92
    iary
    0.87
    anth
    0.82
    hovah
    0.81
    cedented
    0.80
    ancers
    0.79
    ials
    0.78
    uing
    0.78
    ateurs
    0.78
    Activations Density 0.077%

    No Known Activations