© 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. 15952
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations and official bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and committees

    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
     disg
    -0.72
    ĻĤ
    -0.69
     peril
    -0.68
     legend
    -0.65
     derivative
    -0.62
     alarms
    -0.61
     batter
    -0.61
     ripple
    -0.61
     inconven
    -0.59
     brighter
    -0.59
    POSITIVE LOGITS
     Against
    1.16
     Of
    0.89
     Provision
    0.84
     of
    0.82
    apego
    0.82
     Interface
    0.77
    ozo
    0.75
    Of
    0.75
     Computing
    0.73
     Coord
    0.72
    Activations Density 0.209%

    No Known Activations