© 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. 6-RES-JB
    11. 17639
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and instructions

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases that indicate a connection or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    living
    -0.66
    tions
    -0.64
    financial
    -0.64
    pants
    -0.63
    ippi
    -0.62
    tin
    -0.62
    question
    -0.62
    furt
    -0.61
    woman
    -0.60
    typ
    -0.59
    POSITIVE LOGITS
    ggles
    1.36
     maximize
    1.32
     ensure
    1.26
     minimize
    1.23
     enhance
    1.21
     optimize
    1.19
     simulate
    1.13
     achieve
    1.13
     determine
    1.13
     emulate
    1.12
    Activations Density 0.272%

    No Known Activations