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. 10-RES-JB
    6. 14753
    Prev
    Next
    INDEX
    Explanations

    text related to online scams, fraudulent activities, and illegal behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to scams and fraudulent activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.86
    ĪĴ
    -0.86
    equal
    -0.74
    natureconservancy
    -0.72
    +++
    -0.71
    adj
    -0.69
    inguished
    -0.69
    Phys
    -0.68
    mosp
    -0.66
    eatures
    -0.66
    POSITIVE LOGITS
     extortion
    1.33
     fraudulent
    1.29
     scams
    1.24
     traffickers
    1.23
     ransom
    1.22
     prostitutes
    1.22
     bribes
    1.21
     blackmail
    1.21
     disgu
    1.20
     unwitting
    1.20
    Activations Density 0.589%

    No Known Activations