© 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. 1833
    Prev
    Next
    INDEX
    Explanations

    unexpected or unusual events

    oai_token-act-pair · gpt-3.5-turbo

    unexpected or remarkable events and phenomena

    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
    verning
    -0.69
     certific
    -0.69
    addy
    -0.64
    versely
    -0.64
     dominant
    -0.64
    osponsors
    -0.63
     tense
    -0.63
     GOODMAN
    -0.63
     stern
    -0.62
    earchers
    -0.61
    POSITIVE LOGITS
     imaginable
    0.72
    ulence
    0.71
     conco
    0.68
     awaits
    0.68
    manship
    0.64
    fell
    0.64
     involving
    0.64
     considering
    0.63
     indeed
    0.63
     stunts
    0.62
    Activations Density 0.472%

    No Known Activations