© 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. 10-RES-JB
    11. 5519
    Prev
    Next
    INDEX
    Explanations

    brief phrases or sentences related to reviews or critiques

    oai_token-act-pair · gpt-3.5-turbo

    nouns and specific terms related to cultural references or societal elements

    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
    igenous
    -0.70
    escription
    -0.69
     Incre
    -0.68
    ãĤ¹ãĥĪ
    -0.66
    ä¹ĭ
    -0.65
    orthy
    -0.65
    asury
    -0.64
    Background
    -0.64
    izont
    -0.63
    erenn
    -0.63
    POSITIVE LOGITS
     ain
    1.28
     forgot
    1.25
     kinda
    1.23
     bullshit
    1.18
     gotta
    1.18
     crap
    1.18
     dude
    1.16
     pissed
    1.13
     wanna
    1.11
     dudes
    1.11
    Activations Density 0.617%

    No Known Activations