© 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. 6744
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds or materials

    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
    214
    +0.12
    0.5%
    36
    +0.10
    0.5%
    631
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.12
    0.01
    57
    +0.10
    0.01
    588
    +0.10
    0.01
    Negative Logits
    ALLY
    -0.64
     Yor
    -0.64
    !/
    -0.64
    bucks
    -0.64
     ads
    -0.63
     Dynamics
    -0.59
     calendars
    -0.58
    packing
    -0.58
     Surveillance
    -0.57
     advertising
    -0.56
    POSITIVE LOGITS
    utions
    1.24
    uter
    1.10
    esar
    1.05
    ution
    1.04
    ppy
    1.04
    pping
    1.01
    ffer
    1.00
    fter
    0.96
    ust
    0.94
    ud
    0.93
    Activations Density 0.022%

    No Known Activations