© 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. 4-RES-JB
    11. 117
    Prev
    Next
    INDEX
    Explanations

    place names in conflict zones

    oai_token-act-pair · gpt-3.5-turbo

    place names and geographical references

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

    No Comments

    Negative Logits
     Roth
    -0.78
    Lear
    -0.73
    Magn
    -0.71
     Greenberg
    -0.71
     BAT
    -0.66
     OW
    -0.65
    Pitt
    -0.65
     Sirius
    -0.64
    urer
    -0.62
     watt
    -0.61
    POSITIVE LOGITS
    istan
    1.24
     Lumpur
    1.04
     Pradesh
    0.98
     Province
    0.93
     countryside
    0.91
    oglu
    0.88
    uala
    0.88
     Peninsula
    0.87
    icho
    0.86
     peninsula
    0.84
    Activations Density 0.143%

    No Known Activations