© 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. 11-RES-JB
    11. 5169
    Prev
    Next
    INDEX
    Explanations

    specific terms or vocabulary words

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thumbnails
    -0.61
    jri
    -0.61
    imeo
    -0.60
     srfAttach
    -0.60
     detrim
    -0.59
    akis
    -0.58
    HCR
    -0.57
     trave
    -0.56
    udeau
    -0.56
    aukee
    -0.55
    POSITIVE LOGITS
     coined
    1.31
    ciation
    1.19
     referring
    1.18
     meaning
    1.09
     describing
    1.00
     loosely
    0.97
     shorthand
    0.97
     suffix
    0.96
     synonymous
    0.96
     used
    0.94
    Activations Density 0.111%

    No Known Activations