© 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. 17333
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to varied subjects, potentially from pop culture references

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific video game franchises and characters

    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
     Democr
    -0.78
    imately
    -0.65
     GOODMAN
    -0.62
     UNCLASSIFIED
    -0.62
    cled
    -0.62
    resso
    -0.59
    regon
    -0.59
    allo
    -0.58
    ndra
    -0.57
     bordering
    -0.57
    POSITIVE LOGITS
    ggle
    0.67
    Ultra
    0.64
    zees
    0.64
    zu
    0.62
    iverse
    0.61
    Jump
    0.61
    kit
    0.59
    ikuman
    0.59
    isphere
    0.58
    zee
    0.58
    Activations Density 0.207%

    No Known Activations