© 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. 5633
    Prev
    Next
    INDEX
    Explanations

    terms related to health hazards and potential risks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of substances or materials

    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
    Recomm
    -0.68
     Ashes
    -0.67
    laughs
    -0.64
    BUG
    -0.61
    Honest
    -0.61
    ALLY
    -0.60
    Brother
    -0.59
    Finish
    -0.57
    Fla
    -0.55
    Unknown
    -0.54
    POSITIVE LOGITS
     are
    1.44
     aren
    1.32
     were
    1.27
     belong
    1.21
     comprise
    1.17
     contain
    1.17
     constitute
    1.16
     represent
    1.16
     weren
    1.12
     consist
    1.11
    Activations Density 0.336%

    No Known Activations