© 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. 4620
    Prev
    Next
    INDEX
    Explanations

    phrases related to support or feedback provided by a community

    oai_token-act-pair · gpt-3.5-turbo

    expressions of support and encouragement for contributions and community engagement

    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
     Purg
    -0.86
    chwitz
    -0.70
    phis
    -0.70
     Brun
    -0.64
    BSD
    -0.63
    luaj
    -0.62
    hid
    -0.62
     nudity
    -0.61
    sterdam
    -0.61
     Classes
    -0.60
    POSITIVE LOGITS
     influence
    1.30
     Influence
    1.23
     impact
    1.22
     influencing
    1.18
     pivotal
    1.13
    impact
    1.12
     invaluable
    1.08
     help
    1.02
     contribute
    1.00
     helping
    0.98
    Activations Density 1.202%

    No Known Activations