© 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. 9-RES-JB
    11. 4623
    Prev
    Next
    INDEX
    Explanations

    concluding statements, often starting with "After all" and followed by a related statement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "after all."

    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
    pec
    -0.77
    MpServer
    -0.72
    agnetic
    -0.67
    ificantly
    -0.66
    Near
    -0.65
    alysed
    -0.65
    xon
    -0.63
    icia
    -0.63
    ocated
    -0.63
    iHUD
    -0.62
    POSITIVE LOGITS
     why
    0.97
     nobody
    0.94
     imagine
    0.87
     suppose
    0.86
     wouldn
    0.83
    nob
    0.80
     hey
    0.78
     isn
    0.78
    why
    0.77
     if
    0.77
    Activations Density 0.174%

    No Known Activations