© 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. 11-RES-JB
    11. 6990
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or areas

    oai_token-act-pair · gpt-3.5-turbo

    references to cities and local contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Purs
    -0.62
    idate
    -0.57
    chieve
    -0.57
    awaru
    -0.56
     confir
    -0.56
     culminated
    -0.55
     succeeds
    -0.54
     Straw
    -0.53
    ukong
    -0.53
     puzz
    -0.52
    POSITIVE LOGITS
     anyways
    1.11
     whereas
    1.04
     anyway
    1.01
     nowadays
    0.90
     comparatively
    0.83
     unlike
    0.82
     so
    0.81
     rather
    0.80
     :(
    0.79
     (~
    0.78
    Activations Density 0.607%

    No Known Activations