© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10641
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or incidents happening in a specific place

    oai_token-act-pair · gpt-3.5-turbo

    repetitive punctuation or sentence fragments

    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
     booking
    -0.66
     favour
    -0.65
     booked
    -0.65
    abies
    -0.63
     microphones
    -0.61
     cameras
    -0.61
    onite
    -0.61
    */(
    -0.59
     ($)
    -0.58
     heads
    -0.56
    POSITIVE LOGITS
     .
    1.72
     ."
    1.50
     .)
    1.41
    _.
    1.30
    -.
    1.24
     ._
    1.21
     ..
    1.17
    ,.
    1.05
     (.
    0.95
    `.
    0.91
    Activations Density 0.020%

    No Known Activations