© 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. 10-RES-JB
    11. 10590
    Prev
    Next
    INDEX
    Explanations

    information related to law schools

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law schools and legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.78
    IBLE
    -0.69
    Ò
    -0.65
     captcha
    -0.62
    atomic
    -0.61
    hetic
    -0.60
     gobl
    -0.60
    emonic
    -0.59
     Daylight
    -0.59
     Cinnamon
    -0.58
    POSITIVE LOGITS
    yer
    1.66
    suit
    1.55
    rence
    1.50
    yers
    1.43
    suits
    1.39
     Enforcement
    1.25
    makers
    1.19
     enforcement
    1.18
    rences
    1.16
    maker
    1.08
    Activations Density 0.037%

    No Known Activations