© 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. 0-RES-JB
    11. 1234
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual named "Johansen"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, particularly related to their accomplishments or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vet
    -0.66
     fel
    -0.64
     pot
    -0.64
     Shade
    -0.62
    pat
    -0.61
     Pot
    -0.60
     Tig
    -0.60
     rotting
    -0.60
    ially
    -0.59
     grade
    -0.58
    POSITIVE LOGITS
    ansen
    4.31
    ansson
    3.31
    anson
    2.57
    ensen
    1.56
    ockey
    1.43
     Hansen
    1.31
    ancock
    1.22
    iggins
    1.15
    ussen
    1.12
    onen
    1.10
    Activations Density 0.017%

    No Known Activations