© 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. 7-RES-JB
    11. 205
    Prev
    Next
    INDEX
    Explanations

    words related to spiraling or uncontrollable movements or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to spirals, particularly in various contexts and descriptions

    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
    Hispanic
    -0.84
    ropolitan
    -0.73
    ourke
    -0.68
    POS
    -0.66
    prototype
    -0.65
    orkshire
    -0.65
    orate
    -0.64
    endment
    -0.63
     cler
    -0.61
    OTA
    -0.61
    POSITIVE LOGITS
     spiral
    1.09
     spir
    1.03
     staircase
    0.91
     Spiral
    0.81
    rily
    0.81
    iflower
    0.78
    chart
    0.76
    uler
    0.75
    aceous
    0.72
    ilon
    0.72
    Activations Density 0.051%

    No Known Activations