© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 6639
    Prev
    Next
    INDEX
    Explanations

    terms related to discrimination and extremism

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments related to various forms of discrimination and extremism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laure
    -0.74
    ĸļ
    -0.73
     precincts
    -0.73
     Anniversary
    -0.71
     curled
    -0.70
     scratch
    -0.69
     fold
    -0.69
     thumbnail
    -0.69
     Brus
    -0.68
     somew
    -0.68
    POSITIVE LOGITS
    Semitic
    1.68
    Semitism
    1.61
    establishment
    1.54
    government
    1.50
    immigrant
    1.49
    democratic
    1.45
    social
    1.44
    capitalist
    1.44
    choice
    1.39
    immigration
    1.35
    Activations Density 0.022%

    No Known Activations