© 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. 8-RES-JB
    11. 11703
    Prev
    Next
    INDEX
    Explanations

    phrases related to building on previous ideas or momentum

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the idea of building or progressing on existing foundations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pid
    -0.80
     Penguins
    -0.71
    lys
    -0.67
    ãĥı
    -0.66
    ura
    -0.66
    cgi
    -0.66
    Tax
    -0.65
    oped
    -0.65
    otted
    -0.64
    iform
    -0.64
    POSITIVE LOGITS
     momentum
    0.92
     groundwork
    0.90
     existing
    0.89
     tradition
    0.88
     foundations
    0.84
     laure
    0.79
     behalf
    0.79
     successes
    0.76
     principles
    0.75
     foundation
    0.75
    Activations Density 0.102%

    No Known Activations