© 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. 11388
    Prev
    Next
    INDEX
    Explanations

    specific terms related to databases and technical subjects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological databases and research

    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
     modesty
    -0.69
     attendance
    -0.68
     failing
    -0.67
     Balt
    -0.62
     refrain
    -0.61
     persu
    -0.59
     Christensen
    -0.58
     exempted
    -0.57
     belie
    -0.56
     diplom
    -0.56
    POSITIVE LOGITS
    ilit
    1.19
    acteria
    1.16
    oard
    1.13
    udd
    1.10
    irds
    1.10
    acter
    1.10
    iotics
    1.08
    onds
    1.08
    urger
    1.07
    iotic
    1.06
    Activations Density 0.051%

    No Known Activations