© 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. 10-RES_POST_32K-OAI
    11. 28688
    Prev
    Next
    INDEX
    Explanations

    occurrences of press conferences and their context in news reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    378
    +0.13
    0.6%
    258
    +0.12
    0.6%
    532
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.13
    0.06
    547
    +0.12
    0.03
    132
    +0.11
    0.03
    Negative Logits
    AFTA
    -0.65
    wikipedia
    -0.65
     Prosper
    -0.61
     Bastard
    -0.61
     dissertation
    -0.60
    istries
    -0.59
     fixme
    -0.59
    jac
    -0.59
    JP
    -0.58
    vol
    -0.58
    POSITIVE LOGITS
     announcing
    1.13
     afterward
    0.83
     unveiling
    0.81
     briefing
    0.77
     flanked
    0.77
    accompanied
    0.76
     aboard
    0.74
     afterwards
    0.74
    ack
    0.74
    irming
    0.73
    Activations Density 0.331%

    No Known Activations