© 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. 20045
    Prev
    Next
    INDEX
    Explanations

    instances of medical terms and potentially traumatic events

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional experiences and social interactions

    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
     embod
    -0.56
     encomp
    -0.55
    existent
    -0.51
     allegiance
    -0.51
    igmatic
    -0.51
     acronym
    -0.51
     "'
    -0.50
     artic
    -0.50
    worldly
    -0.50
    âĦ¢:
    -0.49
    POSITIVE LOGITS
     regained
    0.85
     thereafter
    0.82
     then
    0.81
     therefore
    0.81
     meanwhile
    0.81
     resumed
    0.80
     afterwards
    0.80
     reverted
    0.80
     however
    0.77
    sequently
    0.76
    Activations Density 1.160%

    No Known Activations