© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 24269
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "boro"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations, particularly names related to 'boro' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pert
    -0.84
    prem
    -0.82
    Prem
    -0.74
    External
    -0.69
    effective
    -0.68
    demand
    -0.68
    defined
    -0.67
    Minimum
    -0.66
    efficient
    -0.66
    dm
    -0.65
    POSITIVE LOGITS
    boro
    1.52
     Baptist
    0.89
    hurst
    0.84
    burgh
    0.82
    halla
    0.82
     Boys
    0.79
    borg
    0.75
    ertodd
    0.75
    rats
    0.73
    eno
    0.72
    Activations Density 0.005%

    No Known Activations