© 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. 8-RES-JB
    11. 1023
    Prev
    Next
    INDEX
    Explanations

    geographical locations and natural elements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various racial and ethnic groups, along with references to environmental and geological phenomena

    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
     Patreon
    -0.73
     Canaver
    -0.61
    ĸļ
    -0.59
     Startup
    -0.58
    OSED
    -0.57
     Electoral
    -0.57
    uncture
    -0.57
    afety
    -0.57
    wikipedia
    -0.56
     CASE
    -0.56
    POSITIVE LOGITS
     hybrids
    0.82
    resses
    0.78
     diseases
    0.71
    ampires
    0.70
    oids
    0.70
     drones
    0.68
     dams
    0.67
     disorders
    0.66
     predators
    0.66
     alike
    0.65
    Activations Density 0.566%

    No Known Activations