© 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. 10680
    Prev
    Next
    INDEX
    Explanations

    names of specific locations or destinations

    oai_token-act-pair · gpt-3.5-turbo

    names of geographical locations

    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
    stood
    -0.70
     resemblance
    -0.64
     pse
    -0.55
     indicators
    -0.55
     ingenious
    -0.54
     Meter
    -0.52
     nutshell
    -0.52
    athered
    -0.51
    icators
    -0.51
    sheet
    -0.51
    POSITIVE LOGITS
     via
    0.91
     destinations
    0.90
     aboard
    0.90
     airport
    0.82
     whence
    0.79
     for
    0.76
     shores
    0.75
     where
    0.74
     ASAP
    0.73
     Springs
    0.72
    Activations Density 0.245%

    No Known Activations