© 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 EvalsExportsAPI 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. 9-RES-JB
    11. 19497
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms related to transactions and mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to financial and structural concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.72
    tics
    -0.71
    ãĥĥãĥī
    -0.65
     Blacks
    -0.65
    doms
    -0.65
     Reps
    -0.64
     Rooms
    -0.63
     Halls
    -0.62
     Pets
    -0.61
    CI
    -0.61
    POSITIVE LOGITS
     exists
    1.37
     emerges
    1.36
     awaits
    1.30
     ensued
    1.24
     existed
    1.17
     emerged
    1.15
     arises
    1.13
     arose
    1.10
     occurs
    1.08
     sprang
    1.08
    Activations Density 0.480%

    No Known Activations