© 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. 9-RES-JB
    11. 14725
    Prev
    Next
    INDEX
    Explanations

    various forms and versions of something

    oai_token-act-pair · gpt-3.5-turbo

    references to different forms and variations of concepts or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cientious
    -0.63
    olic
    -0.60
    Zone
    -0.60
    SPONSORED
    -0.60
    chi
    -0.60
    orts
    -0.58
     Hurricanes
    -0.57
     Phelps
    -0.56
    ahon
    -0.56
     quotas
    -0.56
    POSITIVE LOGITS
     form
    0.93
     Became
    0.74
    morph
    0.73
     shape
    0.71
     psychiat
    0.71
     itself
    0.71
     forms
    0.70
    ï¸
    0.70
     apiece
    0.67
     ubiqu
    0.66
    Activations Density 0.681%

    No Known Activations