© 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. 8-RES-JB
    11. 2765
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and global issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inacc
    -0.56
     cipher
    -0.55
     "%
    -0.55
     Ake
    -0.53
     negotiator
    -0.53
     dossier
    -0.53
     suggestion
    -0.52
     plaque
    -0.52
     odor
    -0.52
     haircut
    -0.52
    POSITIVE LOGITS
    heastern
    0.93
    outheastern
    0.91
     mainland
    0.81
     elsewhere
    0.79
     coasts
    0.78
    outheast
    0.77
    region
    0.77
    orthern
    0.74
    Europe
    0.74
     territories
    0.73
    Activations Density 0.797%

    No Known Activations