© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 20670
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong impact or emphasis, such as 'come true' or 'pendent'

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating truth or reliability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.58
    omal
    -0.56
    ouched
    -0.52
    athered
    -0.52
    uable
    -0.52
    licted
    -0.51
    iva
    -0.51
    ilateral
    -0.50
    lict
    -0.50
    oreal
    -0.50
    POSITIVE LOGITS
     :)
    0.74
     ;)
    0.72
     :-)
    0.62
     ¯
    0.60
     since
    0.60
     ðŁĻĤ
    0.58
     regarding
    0.58
     haha
    0.57
    :
    0.57
    ↵↵
    0.55
    Activations Density 0.960%

    No Known Activations