© 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. 1-RES-JB
    11. 3174
    Prev
    Next
    INDEX
    Explanations

    geographical locations related to Antarctica

    oai_token-act-pair · gpt-3.5-turbo

    references to Antarctica and its geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rog
    -0.86
    hood
    -0.83
    HUD
    -0.82
    ndra
    -0.76
    Rate
    -0.76
    nda
    -0.76
    --------------------------------------------------------
    -0.74
    ducers
    -0.74
    nc
    -0.71
    nd
    -0.71
    POSITIVE LOGITS
     Antarctic
    1.06
     Antarctica
    0.96
    uckland
    0.83
     Yard
    0.81
     Tasmania
    0.79
     glac
    0.79
    ctica
    0.77
     Expedition
    0.77
     gelatin
    0.74
     iceberg
    0.72
    Activations Density 0.006%

    No Known Activations