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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 13029
    Prev
    Next
    INDEX
    Explanations

    references to political ideologies or movements associated with the term "neo."

    oai_token-act-pair · gpt-3.5-turbo

    references to neo-Nazi ideology and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.89
    ORED
    -0.80
    ãĤ¼ãĤ¦ãĤ¹
    -0.79
    Interstitial
    -0.79
    loo
    -0.79
    hips
    -0.79
    worthiness
    -0.77
    channelAvailability
    -0.77
    lessly
    -0.73
    ULL
    -0.72
    POSITIVE LOGITS
    ge
    0.95
     neo
    0.76
    flex
    0.75
    emer
    0.73
    -
    0.73
    azi
    0.73
    fer
    0.73
    chal
    0.71
     mascul
    0.70
    fascist
    0.69
    Activations Density 0.009%

    No Known Activations