© 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 EvalsExportsinterp-engineNEWAPI 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. 10396
    Prev
    Next
    INDEX
    Explanations

    references to technology products and updates

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to technology upgrades and product releases

    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
     degraded
    -0.70
    opathic
    -0.66
    seless
    -0.65
     humanities
    -0.61
     degrade
    -0.60
     dehuman
    -0.59
     discriminated
    -0.58
    isine
    -0.58
     degrading
    -0.58
     campuses
    -0.57
    POSITIVE LOGITS
     rumours
    1.24
     speculation
    1.17
     rumors
    1.16
     rumor
    1.14
     rumored
    1.12
    Rum
    1.10
     speculated
    1.01
     Rum
    1.00
    confirmed
    0.99
     hinted
    0.98
    Activations Density 1.116%

    No Known Activations