© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    words related to political ideologies or movements, specifically the alt-right

    oai_token-act-pair · gpt-3.5-turbo

    negative associations with the alt-right movement

    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
     CGI
    -0.70
     Patron
    -0.67
     destro
    -0.66
    onse
    -0.62
     ND
    -0.62
     Effective
    -0.61
     Coverage
    -0.60
     payable
    -0.60
     IMAGES
    -0.60
     Headquarters
    -0.60
    POSITIVE LOGITS
    matter
    0.92
    weekly
    0.91
    wealth
    0.88
    Atlantic
    0.86
    dial
    0.86
    species
    0.85
    loader
    0.85
    European
    0.84
    Raid
    0.83
    generic
    0.82
    Activations Density 0.040%

    No Known Activations