© 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. 10-RES_POST_32K-OAI
    11. 28657
    Prev
    Next
    INDEX
    Explanations

    aspects of online shopping experiences and user engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    39
    +0.14
    0.6%
    459
    +0.11
    0.5%
    326
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.14
    0.14
    39
    +0.11
    0.14
    51
    +0.11
    0.13
    Negative Logits
     prophes
    -0.73
     Representatives
    -0.71
     insin
    -0.69
     publicized
    -0.67
     Plaint
    -0.67
     patri
    -0.66
     coercive
    -0.65
     circulated
    -0.64
    announced
    -0.64
     prov
    -0.64
    POSITIVE LOGITS
     ;)
    1.14
     browsing
    1.10
     :)
    1.08
     :-)
    1.06
     typing
    0.99
     downloading
    0.98
     experimenting
    0.97
     ðŁĻĤ
    0.97
     installing
    0.93
     debugging
    0.91
    Activations Density 2.426%

    No Known Activations