© 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. 4-RES-JB
    11. 4235
    Prev
    Next
    INDEX
    Explanations

    the name "Bruno" and related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or groups named Bruno and Roma

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

    No Comments

    Negative Logits
    mable
    -0.97
    ming
    -0.80
    sworth
    -0.76
    mers
    -0.74
    uable
    -0.73
    ido
    -0.73
    amental
    -0.73
    orically
    -0.72
    alach
    -0.71
    med
    -0.71
    POSITIVE LOGITS
    culosis
    0.85
     Tenn
    0.71
     Ferdinand
    0.69
     Phant
    0.68
     Kinder
    0.68
     Kirin
    0.68
     Blackburn
    0.67
     Baron
    0.66
     mosqu
    0.65
    LB
    0.63
    Activations Density 0.021%

    No Known Activations