© 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. 6011
    Prev
    Next
    INDEX
    Explanations

    instances of statements that express opinions or evaluations

    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
    356
    +0.09
    0.4%
    689
    +0.09
    0.4%
    372
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.09
    0.06
    512
    +0.09
    0.05
    718
    +0.08
    0.05
    Negative Logits
    cial
    -0.67
    kell
    -0.65
    sense
    -0.63
     dubbed
    -0.59
    atively
    -0.57
    arius
    -0.57
     Patron
    -0.56
     Scarlet
    -0.56
     bells
    -0.56
    ni
    -0.55
    POSITIVE LOGITS
    livion
    0.67
    ĨĴ
    0.65
    ©¶æ
    0.63
     offset
    0.63
     irrelevant
    0.62
    DragonMagazine
    0.61
     beside
    0.61
    ¬¼
    0.59
    CHAPTER
    0.59
    Availability
    0.58
    Activations Density 0.389%

    No Known Activations