© 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. 2-RES-JB
    11. 448
    Prev
    Next
    INDEX
    Explanations

    words related to credentials or qualification documents

    oai_token-act-pair · gpt-4-turbo

    words related to qualifications or certifications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of credentials or related terms regarding verification and validation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trap
    -0.68
    Bed
    -0.64
    effective
    -0.64
     Mast
    -0.63
    upon
    -0.61
    moving
    -0.61
    child
    -0.61
    nav
    -0.61
     Bed
    -0.60
    hearted
    -0.59
    POSITIVE LOGITS
     credentials
    1.61
     credential
    0.99
     qualifications
    0.86
     pedigree
    0.80
     holders
    0.79
     certs
    0.78
    milo
    0.76
     holder
    0.74
     badges
    0.74
    entials
    0.72
    Activations Density 0.008%

    No Known Activations