© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    words related to entities such as organizations, countries, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizations, institutions, and collective groups

    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
    ultimate
    -0.72
    iasis
    -0.69
    oux
    -0.67
    ifest
    -0.66
    ipeg
    -0.62
    odox
    -0.62
    shows
    -0.61
    atever
    -0.59
    ilee
    -0.58
    izoph
    -0.58
    POSITIVE LOGITS
     vying
    0.84
    folk
    0.82
     adopting
    0.80
     have
    0.79
     scrambled
    0.78
     allocate
    0.76
    hare
    0.75
     implementing
    0.75
     employing
    0.75
     adopt
    0.75
    Activations Density 0.292%

    No Known Activations