© 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. 1723
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" combined with a range of follow-up phrases or subjects

    oai_token-act-pair · gpt-3.5-turbo

    statements of personal identity or emotional states

    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
     Gap
    -0.72
     entails
    -0.68
     occurs
    -0.67
     externalToEVAOnly
    -0.66
     lasts
    -0.66
     meets
    -0.65
     Colleges
    -0.64
     Utilities
    -0.63
     looms
    -0.63
    bies
    -0.63
    POSITIVE LOGITS
     glad
    1.24
     thankful
    1.19
     grateful
    1.12
     proud
    1.06
     fortunate
    1.04
     convinced
    1.03
     aware
    1.02
     hoping
    0.99
     honored
    0.99
     amazed
    0.99
    Activations Density 0.119%

    No Known Activations