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. 8-RES-JB
    6. 8885
    Prev
    Next
    INDEX
    Explanations

    the prefix "neo-" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 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
    hips
    -0.89
    uana
    -0.71
    loo
    -0.69
    pring
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
     thumbnail
    -0.67
    channelAvailability
    -0.66
     Qiao
    -0.65
    INESS
    -0.64
    ORED
    -0.63
    POSITIVE LOGITS
    ge
    0.94
    fer
    0.86
    Nazi
    0.86
    azi
    0.82
    flex
    0.78
    iscopal
    0.78
    -
    0.77
    chal
    0.77
    liberal
    0.77
    orthodox
    0.75
    Activations Density 0.025%

    No Known Activations