© 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. 6-RES-JB
    11. 19653
    Prev
    Next
    INDEX
    Explanations

    locations or place names, with a focus on specific cities or localities

    oai_token-act-pair · gpt-3.5-turbo

    the empty token and references to Springfield

    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
    wana
    -1.01
    uana
    -0.95
    mine
    -0.86
    vana
    -0.82
    idi
    -0.80
    anyahu
    -0.77
    ramid
    -0.76
    ird
    -0.76
    orst
    -0.76
    estones
    -0.76
    POSITIVE LOGITS
    shire
    1.01
     Armory
    0.99
     Springfield
    0.78
     Beacon
    0.78
     Heights
    0.75
     skyline
    0.74
     suburbs
    0.74
     Borough
    0.74
     Parish
    0.72
     Township
    0.71
    Activations Density 0.064%

    No Known Activations