© 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. 22558
    Prev
    Next
    INDEX
    Explanations

    locations or addresses

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of places and possibly dates

    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
     environment
    -0.80
    Spoiler
    -0.68
    advertisement
    -0.64
     behavior
    -0.62
    develop
    -0.61
     environments
    -0.60
     behav
    -0.60
     anew
    -0.60
     causation
    -0.59
     supervision
    -0.58
    POSITIVE LOGITS
     Ave
    1.14
     Blvd
    1.07
     Rd
    1.07
     Ct
    0.86
    illion
    0.86
     acres
    0.85
     Points
    0.85
     hrs
    0.82
     STATES
    0.78
     Tickets
    0.78
    Activations Density 0.160%

    No Known Activations