© 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. 0-RES-JB
    11. 19999
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific geographical location - 'Midland'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographic location, particularly "Midland."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    papers
    -0.79
    eering
    -0.71
    agents
    -0.69
     WITHOUT
    -0.67
    SOURCE
    -0.66
    wcs
    -0.66
     forc
    -0.64
    USE
    -0.64
    TED
    -0.63
     photoc
    -0.63
    POSITIVE LOGITS
     Mid
    3.67
    Mid
    2.76
    mid
    2.03
     mid
    1.88
     MID
    1.82
     mids
    1.49
     Midwest
    1.49
     Midnight
    1.27
     Middle
    1.23
    Middle
    1.18
    Activations Density 0.014%

    No Known Activations