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. 7-RES-JB
    6. 6203
    Prev
    Next
    INDEX
    Explanations

    information related to legal actions, sentences, and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with legal sentences and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -1.15
    âĹ¼
    -0.86
     è£ıè
    -0.75
    Ĥª
    -0.72
     âĶľâĶĢâĶĢ
    -0.69
     :=
    -0.68
    theless
    -0.68
    ãĤ¶
    -0.68
    ////////////////////////////////
    -0.67
    brew
    -0.67
    POSITIVE LOGITS
     watchdog
    0.68
     sex
    0.65
     paed
    0.65
     fue
    0.64
     organisers
    0.62
     Nasa
    0.61
     charity
    0.61
     sparking
    0.60
     amid
    0.59
     euth
    0.59
    Activations Density 0.828%

    No Known Activations