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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4629
    Prev
    Next
    INDEX
    Explanations

    words prefixed with 'neo-' related to different ideologies, political groups, and themes

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with neo-Nazi ideology and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ado
    -0.75
    channelAvailability
    -0.74
     bearer
    -0.72
    anwhile
    -0.69
     Coverage
    -0.68
     Beats
    -0.68
     coverage
    -0.68
     emoji
    -0.67
     ahead
    -0.66
     AVG
    -0.66
    POSITIVE LOGITS
    liberal
    1.21
    Nazi
    1.20
    natal
    1.15
    colonial
    1.14
    traditional
    1.12
    fascist
    1.09
    femin
    1.08
    Nazis
    1.07
    conservative
    1.04
    social
    1.03
    Activations Density 0.039%

    No Known Activations