© 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. 10391
    Prev
    Next
    INDEX
    Explanations

    names of public figures and political events

    oai_token-act-pair · gpt-3.5-turbo

    names of people, particularly in political or controversial contexts

    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
    ometimes
    -0.70
     bred
    -0.61
     hardened
    -0.58
    bred
    -0.55
     polymer
    -0.54
     buds
    -0.54
     alike
    -0.53
     crooked
    -0.53
     grind
    -0.53
    conservancy
    -0.53
    POSITIVE LOGITS
    's
    1.37
    ÃŃs
    0.95
    ]'
    0.92
     announcing
    0.90
     joining
    0.85
    \'
    0.82
     declaring
    0.81
    ´
    0.81
     revelations
    0.81
     criticisms
    0.80
    Activations Density 0.384%

    No Known Activations