Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7508
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations or proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conflicts or issues in specific regions, particularly geopolitical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    panic
    -0.69
    roup
    -0.66
    lio
    -0.62
    porter
    -0.57
     Gaul
    -0.57
    gress
    -0.56
    oshenko
    -0.55
    irlf
    -0.54
    INTON
    -0.51
    tti
    -0.51
    POSITIVE LOGITS
    ciating
    0.61
    anu
    0.57
    art
    0.55
     unden
    0.53
    ruct
    0.53
    iable
    0.52
    ruption
    0.51
    zhen
    0.51
     unpop
    0.50
     predec
    0.50
    Activations Density 0.229%

    No Known Activations