© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2859
    Prev
    Next
    INDEX
    Explanations

    keywords related to code syntax and software development

    oai_token-act-pair · gpt-3.5-turbo

    references to multimedia content types and structures

    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
    uckland
    -0.85
    olulu
    -0.83
    ovember
    -0.78
    Madison
    -0.74
    itness
    -0.74
    bush
    -0.74
    orsi
    -0.72
    DERR
    -0.72
    rey
    -0.72
    gow
    -0.71
    POSITIVE LOGITS
     guiActiveUnfocused
    0.80
    livious
    0.77
    application
    0.71
    TEXT
    0.70
     nom
    0.70
     MT
    0.70
    submit
    0.69
    ARCH
    0.68
     ZIP
    0.68
     MED
    0.67
    Activations Density 0.095%

    No Known Activations