© 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. 14767
    Prev
    Next
    INDEX
    Explanations

    the term "email" or words associated with electronic communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "e" in various contexts

    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
     Painter
    -0.65
     Kitchen
    -0.64
     NEC
    -0.64
     Anthem
    -0.64
     Operator
    -0.63
    ãĤ¤ãĥĪ
    -0.61
     Ernst
    -0.60
     vocals
    -0.60
     Activision
    -0.59
     sway
    -0.58
    POSITIVE LOGITS
    tymology
    1.47
    agles
    1.28
    ugen
    1.22
    ternally
    1.22
    ighth
    1.20
    gypt
    1.18
    arthed
    1.16
    pee
    1.15
    thereum
    1.15
    gress
    1.13
    Activations Density 0.031%

    No Known Activations