© 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. 6588
    Prev
    Next
    INDEX
    Explanations

    elements related to social media and online presence

    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
    +0.14
    0.6%
    221
    +0.11
    0.5%
    353
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    0.01
    326
    +0.11
    0.06
    284
    +0.09
    0.05
    Negative Logits
     downgrade
    -0.74
     irrelevant
    -0.70
     reinforced
    -0.70
     depreciation
    -0.69
     repeats
    -0.69
     disadvantage
    -0.69
     mathemat
    -0.67
     stereotyp
    -0.66
     credential
    -0.66
     standby
    -0.65
    POSITIVE LOGITS
    official
    1.05
    /,
    0.97
    Stud
    0.94
    alty
    0.92
    kamp
    0.91
    /)
    0.87
    ertodd
    0.83
    edin
    0.82
    vim
    0.81
    /.
    0.81
    Activations Density 0.479%

    No Known Activations