© 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. 3-RES-JB
    11. 9111
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly justices and politicians

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent individuals, particularly those associated with the judiciary and civil rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alling
    -0.79
    fab
    -0.73
    omics
    -0.72
     Huck
    -0.70
    hof
    -0.70
    aging
    -0.70
    Demand
    -0.70
    inen
    -0.69
    Cra
    -0.68
    ific
    -0.67
    POSITIVE LOGITS
    herty
    0.80
    ton
    0.78
    inav
    0.74
     Parish
    0.72
     TAMADRA
    0.66
    illac
    0.65
     tract
    0.65
    izabeth
    0.64
     Tut
    0.64
    è£ħ
    0.64
    Activations Density 0.026%

    No Known Activations