© 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. 18535
    Prev
    Next
    INDEX
    Explanations

    the names of places

    oai_token-act-pair · gpt-3.5-turbo

    elements related to dramatic or noteworthy events

    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
    Cause
    -0.73
    ossibility
    -0.72
     cannot
    -0.72
     contam
    -0.69
     dunno
    -0.67
     sue
    -0.66
    erity
    -0.65
     violates
    -0.65
    hovah
    -0.64
    },{"
    -0.64
    POSITIVE LOGITS
     Saturday
    0.93
     Thursday
    0.91
     Wednesday
    0.89
     Friday
    0.87
     Tuesday
    0.84
     Sunday
    0.84
     Saturdays
    0.82
     outings
    0.81
     Monday
    0.81
     evenings
    0.81
    Activations Density 0.809%

    No Known Activations