© 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. 6166
    Prev
    Next
    INDEX
    Explanations

    mentions of specific words, such as "Ginger", "Harmon", "Turku", and "gentrification"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ginger and its context within various topics

    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
    AMES
    -0.75
    agher
    -0.75
    arty
    -0.74
    aer
    -0.74
    omsday
    -0.71
    avier
    -0.69
    opus
    -0.68
    obar
    -0.68
     Ragnarok
    -0.68
    ames
    -0.68
    POSITIVE LOGITS
    bread
    0.94
    leness
    0.94
    ité
    0.92
    lers
    0.84
    culosis
    0.73
    led
    0.70
    ler
    0.69
    plug
    0.69
    grounds
    0.68
    lys
    0.68
    Activations Density 0.188%

    No Known Activations