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. 22224
    Prev
    Next
    INDEX
    Explanations

    phrases related to reporting incidents to the police

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement and police

    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
    worn
    -0.85
    NetMessage
    -0.82
    çĭ
    -0.81
    pread
    -0.76
    illion
    -0.71
    ech
    -0.70
    viks
    -0.69
    bub
    -0.69
    eches
    -0.68
    days
    -0.68
    POSITIVE LOGITS
     coroner
    1.18
     Department
    1.13
     Ministry
    1.13
     Bureau
    1.10
     nearest
    1.08
     authorities
    1.04
     FBI
    1.03
     Office
    1.02
     Registrar
    1.02
     Internal
    1.01
    Activations Density 0.270%

    No Known Activations