© 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. 10-RES_POST_32K-OAI
    11. 29984
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to reboots or revisiting past works

    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
    136
    +0.11
    0.5%
    281
    +0.10
    0.5%
    217
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    0.00
    503
    +0.10
    0.02
    232
    +0.09
    0.04
    Negative Logits
    swer
    -0.84
    jriwal
    -0.78
    vantage
    -0.71
    alus
    -0.69
     Benefits
    -0.68
     Syl
    -0.66
     benefits
    -0.65
     Zy
    -0.65
     Buffer
    -0.65
     safeguards
    -0.64
    POSITIVE LOGITS
    issued
    0.92
    edited
    0.87
    imag
    0.86
    release
    0.85
    produced
    0.85
    issue
    0.85
    issues
    0.81
    Untitled
    0.80
    prints
    0.79
    released
    0.76
    Activations Density 0.433%

    No Known Activations