© 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. 6019
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate importance or significance in various contexts

    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
    720
    +0.10
    0.5%
    329
    +0.10
    0.4%
    101
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.10
    0.06
    362
    +0.10
    0.04
    393
    +0.09
    0.06
    Negative Logits
    iatus
    -0.68
     Outbreak
    -0.67
    abus
    -0.67
    olves
    -0.66
     guiActiveUn
    -0.65
    uthor
    -0.64
    igible
    -0.64
    compatible
    -0.63
    washer
    -0.63
    ichick
    -0.62
    POSITIVE LOGITS
     teamwork
    0.98
     preserving
    0.90
     freedoms
    0.90
     individuality
    0.85
     privacy
    0.83
     vigilance
    0.81
     secrecy
    0.79
     confidentiality
    0.79
     anonymity
    0.79
     virginity
    0.78
    Activations Density 0.657%

    No Known Activations