© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18565
    Prev
    Next
    INDEX
    Explanations

    words related to social embarrassment or shame

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "Emb" followed by various suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.84
    ãĥīãĥ©
    -0.76
    creen
    -0.74
    gers
    -0.69
     obsc
    -0.67
     è£ı
    -0.66
    ãĥĥãĥĪ
    -0.66
    heast
    -0.63
    姫
    -0.63
    culosis
    -0.63
    POSITIVE LOGITS
    arrass
    1.45
    edded
    1.31
    odied
    1.27
    assies
    1.16
    attled
    1.09
    argo
    1.07
    assy
    1.05
    odies
    1.05
    edd
    1.00
    olicy
    0.94
    Activations Density 0.059%

    No Known Activations