© 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. 29682
    Prev
    Next
    INDEX
    Explanations

    positive affirmations and self-esteem expressions

    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
    474
    +0.10
    0.4%
    763
    +0.09
    0.4%
    449
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.08
    76
    +0.09
    0.04
    435
    +0.09
    0.03
    Negative Logits
    —-
    -0.92
    —
    -0.82
    ``
    -0.80
    "—
    -0.77
    --
    -0.76
    Reviewer
    -0.74
    Advertisement
    -0.73
    >>>>
    -0.72
    >>>>>>>>
    -0.72
    —"
    -0.72
    POSITIVE LOGITS
     /
    2.76
     (/
    1.37
     "/
    1.32
     [/
    1.22
    /,
    1.14
     '/
    1.14
    ./
    1.13
    !/
    1.09
    =/
    1.08
    )/
    1.06
    Activations Density 1.189%

    No Known Activations