© 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. 9-RES-JB
    11. 5668
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and judicial matters, as well as crime and punishment

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and roots associated with negation or absence

    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
    ovember
    -0.74
     Rica
    -0.70
     Extras
    -0.68
    edIn
    -0.65
     Arabia
    -0.64
     compe
    -0.63
    terday
    -0.63
     Audit
    -0.62
     recre
    -0.61
     Korea
    -0.61
    POSITIVE LOGITS
    iest
    1.49
    liest
    1.36
    osphere
    1.29
    hest
    1.19
    akings
    1.16
    cients
    1.09
    arest
    1.07
    ultimate
    1.04
    most
    1.04
    est
    1.04
    Activations Density 0.407%

    No Known Activations