© 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. 9-RES-JB
    11. 7350
    Prev
    Next
    INDEX
    Explanations

    objects and items being physically placed or positioned in different locations

    oai_token-act-pair · gpt-3.5-turbo

    references to possessions and significant 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
    adjusted
    -0.64
    chy
    -0.58
    ranged
    -0.56
    ERG
    -0.54
    normal
    -0.54
    wcs
    -0.54
     Typical
    -0.53
     IEEE
    -0.52
    ģ«
    -0.52
     EW
    -0.51
    POSITIVE LOGITS
     onto
    1.34
     into
    1.15
     squarely
    1.04
     Into
    0.97
     atop
    0.92
     upon
    0.88
    into
    0.82
     smack
    0.77
     upside
    0.76
     firmly
    0.75
    Activations Density 0.716%

    No Known Activations