© 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 EvalsExportsinterp-engineNEWAPI 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. 7191
    Prev
    Next
    INDEX
    Explanations

    questions or prompts in the text

    oai_token-act-pair · gpt-3.5-turbo

    questions posed in the text

    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
    ICT
    -0.75
    hemy
    -0.64
    roud
    -0.60
    ords
    -0.60
    apsed
    -0.60
    lag
    -0.59
    itton
    -0.59
    ographed
    -0.59
    cloneembedreportprint
    -0.58
     earthqu
    -0.55
    POSITIVE LOGITS
     whether
    1.41
    why
    1.40
     why
    1.34
     WHY
    1.32
     Why
    1.30
    whether
    1.27
    Why
    1.23
    how
    1.16
    Does
    1.15
     How
    1.15
    Activations Density 0.403%

    No Known Activations