© 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. 11-RES-JB
    11. 14362
    Prev
    Next
    INDEX
    Explanations

    monetary values expressed in dollars

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or dollar amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    inders
    -0.64
    VIDIA
    -0.60
    inder
    -0.60
    EStreamFrame
    -0.60
     thumb
    -0.60
    enthal
    -0.58
     imag
    -0.57
     acknow
    -0.54
    fman
    -0.54
    cious
    -0.53
    POSITIVE LOGITS
     84
    1.49
     89
    1.48
     83
    1.47
     82
    1.47
     93
    1.46
     91
    1.46
     92
    1.46
     103
    1.46
     86
    1.45
     88
    1.44
    Activations Density 0.454%

    No Known Activations