© 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. 20892
    Prev
    Next
    INDEX
    Explanations

    terms related to various topics such as comic books, science fiction movies, marathons, political figures, Hollywood studios, sports, and culinary flavors

    oai_token-act-pair · gpt-3.5-turbo

    references to specific genres and characteristics of films and storytelling

    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
    anwhile
    -0.80
    çĶ°
    -0.74
    é¾į
    -0.72
     LIMITED
    -0.63
    YES
    -0.63
     jointly
    -0.61
     Ezek
    -0.60
     Qiao
    -0.60
     Annotations
    -0.59
    FORE
    -0.59
    POSITIVE LOGITS
     anymore
    1.18
     nor
    1.05
     dystop
    0.77
    agra
    0.77
     or
    0.75
     gimmick
    0.73
     fairy
    0.72
     guy
    0.72
     pony
    0.71
    iche
    0.71
    Activations Density 0.671%

    No Known Activations