© 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. 20810
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative portrayals or descriptions involving individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to characters and their roles in narratives, particularly villains and societal issues

    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
    Companies
    -0.69
    atars
    -0.68
    OY
    -0.65
    notations
    -0.65
     accordingly
    -0.65
    Production
    -0.65
    cu
    -0.65
    videos
    -0.64
    Wire
    -0.64
    Tickets
    -0.64
    POSITIVE LOGITS
     sorts
    0.97
     nowhere
    0.95
     paradise
    0.86
     disguise
    0.85
     whom
    0.83
     whose
    0.82
     steroids
    0.82
     contrasts
    0.79
     nutshell
    0.74
     exile
    0.73
    Activations Density 0.295%

    No Known Activations