© 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. 10-RES-JB
    11. 3460
    Prev
    Next
    INDEX
    Explanations

    the phrase "bottom line" or variations related to financial outcomes or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of a "bottom line."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sure
    -0.88
    kson
    -0.75
     warr
    -0.71
    ITED
    -0.66
    cci
    -0.63
    itation
    -0.62
    eworld
    -0.62
    ESCO
    -0.61
    ATIONAL
    -0.60
    issance
    -0.60
    POSITIVE LOGITS
     drawer
    0.98
     line
    0.94
     bracket
    0.91
    line
    0.89
    less
    0.88
    most
    0.82
     layer
    0.82
     shelf
    0.79
     Line
    0.79
     halves
    0.78
    Activations Density 0.024%

    No Known Activations