© 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. 3-RES-JB
    11. 22972
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named "Hagel" and variations of the name "Hagel"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities, particularly the name "Hagel."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âķIJâķIJ
    -0.82
     Scotia
    -0.72
     Âł Âł Âł Âł
    -0.70
     Samoa
    -0.64
    PsyNetMessage
    -0.63
     Advertisement
    -0.63
    @#&
    -0.62
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.61
    bably
    -0.60
     cmd
    -0.58
    POSITIVE LOGITS
    glers
    1.34
    nuts
    1.02
    rats
    0.98
    nut
    0.95
    raph
    0.92
    rat
    0.90
    rid
    0.90
    li
    0.90
    tag
    0.90
    bard
    0.90
    Activations Density 0.004%

    No Known Activations