© 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. 20447
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations, particularly Eurasian and Mongolian references

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical regions and ethnic groups

    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
     thence
    -0.68
    pling
    -0.67
     remem
    -0.66
    metry
    -0.60
    pled
    -0.59
     Levi
    -0.58
     bye
    -0.58
     soda
    -0.57
     fortune
    -0.57
     cum
    -0.57
    POSITIVE LOGITS
    ians
    2.07
    ian
    2.05
    ienne
    1.20
    ican
    1.13
    IAN
    1.09
    ious
    1.05
    ien
    1.05
    ial
    1.03
    ius
    1.03
    ation
    1.02
    Activations Density 0.053%

    No Known Activations