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. 9-RES-JB
    6. 4512
    Prev
    Next
    INDEX
    Explanations

    news-related reports on criminal activities and investigations

    oai_token-act-pair · gpt-3.5-turbo

    incidents related to crime or abuse, particularly sexual offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Newsletter
    -1.10
    ãĢĤ
    -0.79
    colored
    -0.74
    behavior
    -0.74
     è£ıè
    -0.73
     VIDEOS
    -0.72
     UNCLASSIFIED
    -0.72
    .}
    -0.71
    ··
    -0.71
    olor
    -0.69
    POSITIVE LOGITS
     apologise
    1.23
     apologised
    1.18
     paed
    1.15
     organisers
    1.14
     criticised
    1.12
     analyse
    1.06
     analys
    1.04
     recognise
    1.04
     £
    1.03
     centre
    1.02
    Activations Density 0.795%

    No Known Activations