© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 10018
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional information or items

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating supplementary information or additions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uckland
    -0.62
     Fired
    -0.58
     Brothers
    -0.57
    çīĪ
    -0.56
     Guth
    -0.53
     Saras
    -0.52
     Betty
    -0.52
     Kau
    -0.51
     Kon
    -0.51
    ccording
    -0.50
    POSITIVE LOGITS
     thereto
    1.19
     to
    0.91
    ively
    0.79
     thereof
    0.73
    to
    0.73
    aneously
    0.68
    itiz
    0.66
     thereby
    0.64
    ascript
    0.61
    lessly
    0.61
    Activations Density 0.102%

    No Known Activations