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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 18579
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigative processes and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to investigations and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworld
    -0.95
     cakes
    -0.74
     imitation
    -0.74
    ãĤª
    -0.73
     vending
    -0.73
     ç¥ŀ
    -0.70
     widgets
    -0.70
     Brands
    -0.69
     Coca
    -0.69
    osaurs
    -0.68
    POSITIVE LOGITS
     investigative
    1.25
     subpoen
    1.22
     indict
    1.19
     Investigative
    1.16
     Investigations
    1.10
     prosecution
    1.10
     investigations
    1.09
     investigating
    1.09
     subpoena
    1.09
     prosecuting
    1.07
    Activations Density 0.384%

    No Known Activations