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

    Neuronpedia

    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. 2-RES-JB
    11. 9141
    Prev
    Next
    INDEX
    Explanations

    words related to names including "Gosnell", "Gosney", "Ginsburg", and "Biswanath"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and their associations in a legal or controversial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.69
     Crus
    -0.68
     Samoa
    -0.67
     Cel
    -0.65
     Murdoch
    -0.62
     CPC
    -0.62
     floppy
    -0.61
     Immunity
    -0.60
    è¦ļéĨĴ
    -0.60
    inguishable
    -0.60
    POSITIVE LOGITS
     Gos
    0.97
    forth
    0.88
    borg
    0.87
    nell
    0.86
    alez
    0.85
    daq
    0.84
    heng
    0.83
    ÅĤ
    0.82
    ync
    0.82
    boro
    0.81
    Activations Density 0.008%

    No Known Activations