© 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. 9-RES-JB
    11. 15496
    Prev
    Next
    INDEX
    Explanations

    specific mentions of future plans or developments

    oai_token-act-pair · gpt-3.5-turbo

    future actions or predictions

    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
    76561
    -0.72
    CTV
    -0.70
     hating
    -0.69
     dying
    -0.67
     vain
    -0.65
     wounding
    -0.63
     Moment
    -0.61
    hea
    -0.60
    calling
    -0.60
     Syndrome
    -0.60
    POSITIVE LOGITS
     consist
    1.26
     comprise
    1.22
     encompass
    1.11
     be
    1.11
     replace
    1.08
     resemble
    1.04
     include
    1.02
     contain
    1.01
     incorporate
    1.00
     coincide
    0.99
    Activations Density 0.187%

    No Known Activations