© 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. 8-RES-JB
    11. 20466
    Prev
    Next
    INDEX
    Explanations

    phrases related to spatial distribution or extension

    oai_token-act-pair · gpt-3.5-turbo

    elements associated with danger or risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?",
    -0.77
    "))
    -0.72
    estine
    -0.72
    .",
    -0.71
    ondon
    -0.64
    yss
    -0.63
    ukong
    -0.62
    .?
    -0.62
    ena
    -0.61
     Playoffs
    -0.60
    POSITIVE LOGITS
     notwithstanding
    0.65
    ãĥĩãĤ£
    0.64
     loader
    0.60
     unwitting
    0.59
     passers
    0.58
     unsuspecting
    0.58
     nods
    0.57
     accordingly
    0.56
     akin
    0.55
     amid
    0.54
    Activations Density 0.938%

    No Known Activations