© 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. 9-RES-JB
    11. 11191
    Prev
    Next
    INDEX
    Explanations

    statements related to hypothetical scenarios or regrets

    oai_token-act-pair · gpt-3.5-turbo

    references to hypothetical scenarios and conditional statements

    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
    lies
    -0.65
    gae
    -0.62
    ilial
    -0.61
    */(
    -0.59
     externalToEVAOnly
    -0.57
     braces
    -0.57
     nutshell
    -0.55
    DX
    -0.54
    ãĥ¯
    -0.53
    inates
    -0.53
    POSITIVE LOGITS
    would
    1.65
     would
    1.54
     wouldn
    1.45
     Would
    1.45
    Would
    1.27
     Wouldn
    1.19
    'd
    1.13
    could
    1.05
     could
    0.93
    OULD
    0.90
    Activations Density 0.630%

    No Known Activations