© 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. 20088
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing support or opposition

    oai_token-act-pair · gpt-3.5-turbo

    expressions of support for various political issues and proposals

    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
    istical
    -0.81
    æ©Ł
    -0.77
    ixtape
    -0.73
    ngth
    -0.72
     teasp
    -0.70
    orld
    -0.69
    iae
    -0.68
     pione
    -0.68
    DeliveryDate
    -0.67
    ennes
    -0.67
    POSITIVE LOGITS
     legalizing
    1.13
     abol
    1.02
     banning
    0.99
     legalization
    0.99
     repealing
    0.96
     arming
    0.96
     amnesty
    0.92
     adopting
    0.89
     decriminal
    0.89
     independence
    0.88
    Activations Density 0.168%

    No Known Activations