© 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. 2-RES-JB
    11. 12905
    Prev
    Next
    INDEX
    Explanations

    words related to geographic locations, particularly hemispheres

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic regions, specifically the Northern and Western Hemispheres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chard
    -0.97
    DER
    -0.89
    DH
    -0.79
    amin
    -0.78
    Rand
    -0.74
    urat
    -0.74
    Cho
    -0.74
    ERAL
    -0.74
    verbs
    -0.72
    APTER
    -0.71
    POSITIVE LOGITS
     hemisphere
    1.15
     Hemisphere
    1.11
    isphere
    1.07
     lobe
    1.02
     shores
    0.82
     Scrolls
    0.71
     lash
    0.70
     Hispan
    0.69
     coasts
    0.69
     oppressed
    0.68
    Activations Density 0.005%

    No Known Activations