© 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. 24372
    Prev
    Next
    INDEX
    Explanations

    geographic locations and administrative divisions like districts and provinces

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and administrative divisions

    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
    xon
    -0.79
    ometric
    -0.70
    Jones
    -0.69
    erity
    -0.69
    arget
    -0.66
    ober
    -0.65
    ormonal
    -0.62
    Bob
    -0.61
    STAT
    -0.60
    erence
    -0.60
    POSITIVE LOGITS
     âĵĺ
    0.89
     Senegal
    0.88
     northwest
    0.82
     northeast
    0.82
     Borough
    0.80
     southeast
    0.79
     Massacre
    0.77
    ensis
    0.77
    shire
    0.77
     outskirts
    0.77
    Activations Density 0.104%

    No Known Activations