© 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. 6-RES-JB
    11. 17409
    Prev
    Next
    INDEX
    Explanations

    specific locations or regions in the context of various media releases or launches

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and references to specific regions

    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
    zik
    -0.72
    gotten
    -0.70
    rag
    -0.68
    anamo
    -0.68
    role
    -0.68
    ashington
    -0.67
    iasis
    -0.67
    acl
    -0.67
    zinski
    -0.67
    itar
    -0.67
    POSITIVE LOGITS
     NTS
    0.89
     shores
    0.84
    DAQ
    0.82
     indie
    0.79
     markets
    0.76
    ESE
    0.76
     consumers
    0.72
     Indie
    0.72
     OEM
    0.72
     Tes
    0.70
    Activations Density 0.310%

    No Known Activations