© 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. 16962
    Prev
    Next
    INDEX
    Explanations

    settings and configurations terminology, such as macros, adjustments, modifications, and customization options

    oai_token-act-pair · gpt-3.5-turbo

    options and settings related to customization and configuration

    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
     Schwe
    -0.69
    itol
    -0.67
    hillary
    -0.65
    isha
    -0.63
    roots
    -0.63
    angible
    -0.61
    Proof
    -0.61
    orr
    -0.60
    chin
    -0.60
    Jr
    -0.60
    POSITIVE LOGITS
     customize
    1.60
     presets
    1.58
     settings
    1.39
     customization
    1.35
     preset
    1.34
     customizable
    1.32
     tweak
    1.31
     tweaking
    1.30
     config
    1.29
    settings
    1.27
    Activations Density 0.400%

    No Known Activations