© 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. 4-RES-JB
    11. 9062
    Prev
    Next
    INDEX
    Explanations

    references to specific cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cities or references to city-related contexts

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

    No Comments

    Negative Logits
    zees
    -0.97
    chio
    -0.83
    nir
    -0.81
    yip
    -0.78
     Lanka
    -0.77
    dates
    -0.74
    ibaba
    -0.74
    issan
    -0.73
    peria
    -0.73
    iameter
    -0.72
    POSITIVE LOGITS
    wide
    1.21
     council
    1.13
     councillor
    1.06
     attorney
    1.01
     skyline
    0.98
     mayor
    0.95
     ordinance
    0.94
     Council
    0.93
     solicitor
    0.93
     councils
    0.92
    Activations Density 0.041%

    No Known Activations