© 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. 15928
    Prev
    Next
    INDEX
    Explanations

    prepositions "in" indicating involvement or contact

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating involvement or engagement in activities

    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
     bene
    -0.59
    illing
    -0.57
     Balanced
    -0.57
     pall
    -0.54
     EMP
    -0.52
     POL
    -0.52
     mortg
    -0.52
     Croat
    -0.51
     brim
    -0.51
    Ĥª
    -0.51
    POSITIVE LOGITS
    touch
    0.81
     touch
    0.79
    Touch
    0.78
    ked
    0.77
     trouble
    0.75
    aughs
    0.75
    osponsors
    0.73
    emetery
    0.71
    ancial
    0.71
    doors
    0.70
    Activations Density 0.050%

    No Known Activations