Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18758
    Prev
    Next
    INDEX
    Explanations

    phrases related to extremist political views, movements, and groups

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with extremist political ideologies, particularly those on the far right

    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
    ĸļ
    -0.90
     captcha
    -0.78
     Amph
    -0.73
     Yon
    -0.72
     CrossRef
    -0.69
     Dragonbound
    -0.69
     Siem
    -0.68
     Guan
    -0.67
     Cue
    -0.67
     HM
    -0.67
    POSITIVE LOGITS
     extremist
    1.25
    acists
    1.22
     extremists
    1.20
    acist
    1.20
    Islam
    1.16
    fascist
    1.15
    ists
    1.14
     nationalist
    1.13
    femin
    1.13
    Democrats
    1.12
    Activations Density 0.348%

    No Known Activations