© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11110
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement actions

    oai_token-act-pair · gpt-3.5-turbo

    information related to crime and arrests

    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
     sacrific
    -0.75
     Travels
    -0.61
     smack
    -0.59
     helic
    -0.58
    Think
    -0.57
    ometimes
    -0.57
    zon
    -0.56
     Architects
    -0.56
    Zone
    -0.56
    haul
    -0.56
    POSITIVE LOGITS
     nor
    0.95
    yet
    0.87
     forthcoming
    0.86
     whatsoever
    0.85
     yet
    0.84
    ounced
    0.78
    nor
    0.78
     pending
    0.76
     disclosed
    0.72
     officially
    0.71
    Activations Density 0.170%

    No Known Activations