© 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. 10-RES-JB
    11. 10754
    Prev
    Next
    INDEX
    Explanations

    street addresses, specifically focusing on identifying street names and numbers

    oai_token-act-pair · gpt-3.5-turbo

    street names and addresses

    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
    ozy
    -0.82
    ipedia
    -0.75
     legions
    -0.72
     manuals
    -0.61
     competitions
    -0.61
     Canaver
    -0.61
    Disk
    -0.59
    ollah
    -0.58
    Versions
    -0.57
     herds
    -0.57
    POSITIVE LOGITS
     NW
    1.20
     Suite
    1.19
    .,
    1.08
     Blvd
    0.93
     NE
    0.89
    orporated
    0.84
     downtown
    0.83
     SW
    0.82
     SE
    0.81
    wy
    0.81
    Activations Density 0.031%

    No Known Activations