© 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. 8-RES_POST_32K-OAI
    11. 6312
    Prev
    Next
    INDEX
    Explanations

    structures in technical writing

    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
    441
    +0.12
    0.5%
    459
    +0.12
    0.5%
    677
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.04
    160
    +0.12
    0.03
    441
    +0.12
    0.01
    Negative Logits
    isphere
    -0.79
    Enlarge
    -0.73
    tein
    -0.65
    ichick
    -0.65
     âĹı
    -0.64
    enda
    -0.64
    eday
    -0.62
    aban
    -0.62
    ccoli
    -0.62
    Region
    -0.61
    POSITIVE LOGITS
    '),
    0.62
    except
    0.58
    umption
    0.58
    ulative
    0.57
    respective
    0.57
    max
    0.56
    ulic
    0.55
    uctive
    0.55
    weight
    0.54
    oad
    0.54
    Activations Density 0.123%

    No Known Activations