© 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. 8-RES-JB
    11. 16889
    Prev
    Next
    INDEX
    Explanations

    words related to locations or places, specifically with the prefix "St."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation or term "St." followed by geographic locations, particularly cities or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$:/
    -0.78
    hower
    -0.72
    hound
    -0.65
     limited
    -0.64
    ļéĨĴ
    -0.62
     prompt
    -0.61
     tong
    -0.61
    EStream
    -0.59
     friendly
    -0.57
     deaf
    -0.57
    POSITIVE LOGITS
    rict
    1.21
    onew
    1.16
    okes
    1.15
    alker
    1.14
    amps
    1.10
    amped
    1.08
    amping
    1.05
    omach
    1.04
    oppable
    1.04
    olen
    1.04
    Activations Density 0.035%

    No Known Activations