© 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. 6181
    Prev
    Next
    INDEX
    Explanations

    repetitions of the pronoun "he"

    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
    374
    +0.10
    0.5%
    663
    +0.10
    0.5%
    541
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.10
    0.04
    373
    +0.10
    -0.02
    701
    +0.09
    0.03
    Negative Logits
    iott
    -0.75
    DIS
    -0.67
    uckland
    -0.63
    orig
    -0.62
    ipal
    -0.59
    itous
    -0.57
    sterdam
    -0.57
    amaz
    -0.56
    Disk
    -0.56
    DOWN
    -0.55
    POSITIVE LOGITS
    cking
    0.86
    ·
    0.81
    ¹
    0.79
    °
    0.79
    ĵ
    0.78
    ¾
    0.73
    ¶
    0.70
    Ĥ
    0.69
    ģ
    0.68
    ¿
    0.68
    Activations Density 0.186%

    No Known Activations