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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10276
    Prev
    Next
    INDEX
    Explanations

    references to the FBI and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the FBI and its directors or agents

    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
    pain
    -0.71
    pite
    -0.70
     WWF
    -0.70
    opian
    -0.68
    eem
    -0.65
    piring
    -0.64
    plates
    -0.64
    lighting
    -0.64
    galitarian
    -0.63
    lash
    -0.62
    POSITIVE LOGITS
     Agents
    1.08
     informant
    1.07
     investigation
    1.03
     Director
    1.02
    FBI
    0.98
     agents
    0.98
     Inspector
    0.97
     raided
    0.96
     raids
    0.95
     investigates
    0.94
    Activations Density 0.031%

    No Known Activations