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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20757
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations within a larger region

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to geographical locations and their subdivisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.84
    wcsstore
    -0.79
     torped
    -0.76
     istg
    -0.76
    */(
    -0.75
    erity
    -0.73
    chrom
    -0.68
    Versions
    -0.66
    ONS
    -0.66
    ubi
    -0.65
    POSITIVE LOGITS
     southwest
    1.05
     southwestern
    1.04
     southeastern
    1.03
     town
    1.00
     southern
    0.99
     suburb
    0.98
     northwest
    0.97
     northwestern
    0.96
     northeast
    0.95
     southeast
    0.95
    Activations Density 0.157%

    No Known Activations