© 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. 18830
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social discourse

    oai_token-act-pair · gpt-3.5-turbo

    the use of the symbol "ł" and its various contexts related to economic discussions

    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
     buoy
    -0.72
     march
    -0.72
     grate
    -0.69
     salute
    -0.68
     headed
    -0.68
     dome
    -0.68
     sacrific
    -0.68
     bye
    -0.67
     question
    -0.67
     angle
    -0.67
    POSITIVE LOGITS
    their
    1.55
    them
    1.51
    those
    1.45
    your
    1.38
    his
    1.35
    traditional
    1.34
    another
    1.31
    everything
    1.30
    different
    1.29
    these
    1.28
    Activations Density 0.207%

    No Known Activations