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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22219
    Prev
    Next
    INDEX
    Explanations

    mentions of safety and security concerns in public spaces

    oai_token-act-pair · gpt-3.5-turbo

    concerns related to safety and crime

    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
    ģĸ
    -0.87
    equal
    -0.82
    utics
    -0.81
    ãĤ´ãĥ³
    -0.80
    itone
    -0.79
    universal
    -0.78
    assad
    -0.77
    ilateral
    -0.76
    framework
    -0.76
    statement
    -0.76
    POSITIVE LOGITS
     pedestrians
    1.55
     burgl
    1.55
     tresp
    1.52
     thieves
    1.50
     trespass
    1.50
     passers
    1.47
     patrols
    1.44
     robbers
    1.44
     robberies
    1.41
     thefts
    1.37
    Activations Density 0.855%

    No Known Activations