© 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. 0-RES-JB
    11. 11335
    Prev
    Next
    INDEX
    Explanations

    mentions of the city Tuzla

    oai_token-act-pair · gpt-3.5-turbo

    references to the location 'Tuzla'

    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
     Annotations
    -0.74
     Oaks
    -0.70
     greens
    -0.67
     outdoor
    -0.63
     ends
    -0.63
     stake
    -0.61
     fence
    -0.59
     procedural
    -0.59
     notch
    -0.59
     fences
    -0.58
    POSITIVE LOGITS
    uz
    4.45
    uy
    1.39
    enz
    1.29
    oz
    1.25
    uh
    1.17
    uk
    1.17
    uc
    1.15
    ez
    1.14
    iz
    1.14
    udi
    1.14
    Activations Density 0.007%

    No Known Activations