© 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. 6-RES-JB
    11. 11592
    Prev
    Next
    INDEX
    Explanations

    addresses written in a specific format: street, city, state, and postal code

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic locations and address details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WATCHED
    -0.82
    BIP
    -0.68
     batted
    -0.67
    ãģ®éŃĶ
    -0.62
     Flavoring
    -0.61
    âĹ¼
    -0.60
    ADVERTISEMENT
    -0.60
    Pin
    -0.60
    vous
    -0.59
     ultras
    -0.59
    POSITIVE LOGITS
    achine
    0.81
     NW
    0.73
    culosis
    0.73
    agree
    0.71
     Jasper
    0.68
     proble
    0.67
    heast
    0.66
    rg
    0.65
    loo
    0.64
     Carth
    0.64
    Activations Density 0.130%

    No Known Activations