© 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 EvalsExportsinterp-engineNEWAPI 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. 7666
    Prev
    Next
    INDEX
    Explanations

    themes related to emotional depth and human relationships

    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
    387
    +0.10
    0.5%
    494
    +0.10
    0.4%
    19
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.27
    575
    +0.10
    0.19
    325
    +0.10
    0.14
    Negative Logits
     anymore
    -0.67
    ainer
    -0.66
    Article
    -0.65
    License
    -0.64
    )?
    -0.62
    Secondly
    -0.61
     Announce
    -0.60
    Exception
    -0.59
    Valid
    -0.59
     coupon
    -0.59
    POSITIVE LOGITS
     firsthand
    0.92
     vividly
    0.86
     wartime
    0.74
    ,...
    0.74
     eras
    0.73
    turned
    0.72
     heroism
    0.72
     triumph
    0.72
     forgotten
    0.71
     aftermath
    0.70
    Activations Density 5.158%

    No Known Activations