© 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. 7-RES-JB
    11. 24080
    Prev
    Next
    INDEX
    Explanations

    conditions or requirements stated in a formal or legal context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal and regulatory requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uably
    -0.74
    =]
    -0.68
     metaphors
    -0.66
    ãĤ©
    -0.63
     skysc
    -0.62
    Weak
    -0.62
    ĸļ
    -0.62
    pheus
    -0.62
    optim
    -0.61
    Revolution
    -0.60
    POSITIVE LOGITS
     eligibility
    1.00
     receipt
    0.95
     waiver
    0.93
     eligible
    0.91
     specified
    0.91
     enrol
    0.89
     statutory
    0.85
     fee
    0.84
     certificate
    0.84
     waivers
    0.84
    Activations Density 1.006%

    No Known Activations