© 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. 1-RES-JB
    11. 20083
    Prev
    Next
    INDEX
    Explanations

    mentions of the organization "bureau"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "bureau" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.79
    igo
    -0.69
    dash
    -0.68
     Spa
    -0.66
    VID
    -0.66
    shows
    -0.64
    allows
    -0.64
    docker
    -0.63
    forcing
    -0.63
    vo
    -0.62
    POSITIVE LOGITS
     bureau
    1.28
    ureau
    0.85
     Bureau
    0.76
    sonian
    0.74
     tipped
    0.74
     mishand
    0.73
     Debor
    0.70
     correspondent
    0.69
     translator
    0.68
     informant
    0.68
    Activations Density 0.003%

    No Known Activations