© 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 EvalsExportsinterp-engineNEWAPI 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. 18767
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and significant entities in the text

    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
    âĶģ
    -0.68
     recent
    -0.66
     lately
    -0.66
    =-=-=-=-
    -0.64
     avoiding
    -0.62
     tomorrow
    -0.62
     tonight
    -0.61
     nowadays
    -0.60
    endif
    -0.60
    ggle
    -0.58
    POSITIVE LOGITS
     announced
    1.22
     launched
    1.21
     became
    1.17
     began
    1.16
     unveiled
    1.16
     embarked
    1.13
     debuted
    1.12
     undertook
    1.12
     underwent
    1.10
     published
    1.09
    Activations Density 0.348%

    No Known Activations