© 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. 6341
    Prev
    Next
    INDEX
    Explanations

    instances of free events and performances

    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
    481
    +0.71
    11.2%
    373
    +0.13
    2.0%
    480
    +0.04
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.71
    0.58
    547
    +0.13
    -0.03
    225
    +0.04
    0.10
    Negative Logits
     caut
    -0.18
     trave
    -0.18
     destro
    -0.18
     pse
    -0.16
    lvl
    -0.16
     indo
    -0.15
     contrace
    -0.15
     exch
    -0.15
     ende
    -0.14
     arrang
    -0.14
    POSITIVE LOGITS
    blance
    0.17
    owered
    0.16
    etheless
    0.16
    ÂŃ
    0.14
    Brexit
    0.14
    )—
    0.14
    isode
    0.14
    hya
    0.13
    powered
    0.13
     nonetheless
    0.13
    Activations Density 45.406%

    No Known Activations