© 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. 4-RES-JB
    11. 22319
    Prev
    Next
    INDEX
    Explanations

    words related to certificates or legal documents

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of certificates and documentation

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

    No Comments

    Negative Logits
     Holt
    -0.76
     Lank
    -0.74
     Seasons
    -0.67
    axies
    -0.66
    ky
    -0.65
    Ó
    -0.65
    hm
    -0.63
     Barg
    -0.61
     Blooming
    -0.60
    Connell
    -0.60
    POSITIVE LOGITS
    ificate
    1.34
     certificates
    1.08
     certificate
    1.06
     revocation
    0.96
    istry
    0.94
     holder
    0.92
     Certificate
    0.87
     revoked
    0.83
     cert
    0.83
     vit
    0.82
    Activations Density 0.009%

    No Known Activations