© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 20291
    Prev
    Next
    INDEX
    Explanations

    phrases related to regrouping

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health insurance and group coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     analogue
    -0.68
     proof
    -0.64
     burning
    -0.64
     ev
    -0.63
     Dreams
    -0.62
     analog
    -0.62
     taps
    -0.61
     HDMI
    -0.61
     DI
    -0.60
     eternal
    -0.60
    POSITIVE LOGITS
    roup
    4.90
    roups
    2.95
    allery
    1.41
    group
    1.10
    glers
    1.07
    athering
    1.07
    uild
    1.07
    anwhile
    1.07
    GROUP
    1.04
    rosso
    1.04
    Activations Density 0.026%

    No Known Activations