© 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. 6-RES-JB
    11. 7840
    Prev
    Next
    INDEX
    Explanations

    locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations, particularly those labeled as "east" or "west."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     istg
    -0.80
    vous
    -0.79
     reluct
    -0.78
    Deal
    -0.77
    Number
    -0.74
    TABLE
    -0.73
    wcsstore
    -0.72
    abilia
    -0.72
    andom
    -0.72
    thood
    -0.71
    POSITIVE LOGITS
    ward
    1.17
    side
    1.15
    wards
    1.02
     coast
    0.93
     hemisphere
    0.83
     side
    0.80
     wing
    0.78
     west
    0.78
    bound
    0.78
    west
    0.77
    Activations Density 0.028%

    No Known Activations