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. 12580
    Prev
    Next
    INDEX
    Explanations

    mentions of protection, concern for well-being, and potential risks to individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to the lives and wellbeing of individuals or groups within society

    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
    NetMessage
    -0.73
    wcsstore
    -0.73
    ©¶æ¥µ
    -0.71
    adan
    -0.71
    ÅĤ
    -0.71
    cano
    -0.69
    ritis
    -0.69
    etsk
    -0.68
    ocations
    -0.67
    amb
    -0.66
    POSITIVE LOGITS
     individuals
    0.83
     those
    0.78
     sorts
    0.71
     course
    0.70
     citizens
    0.69
     others
    0.69
     Nations
    0.68
     ordinary
    0.67
     Individuals
    0.66
    icial
    0.65
    Activations Density 0.249%

    No Known Activations