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. 9-RES-JB
    6. 12450
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, especially those related to a specific project or event

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Dakota Access Pipeline and related geographical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Britann
    -0.80
    isations
    -0.74
    crow
    -0.68
    icals
    -0.65
     Notting
    -0.65
    fully
    -0.62
    atically
    -0.62
    bnb
    -0.62
    edi
    -0.62
     charism
    -0.62
    POSITIVE LOGITS
     Falls
    1.27
     Montana
    1.01
    adelphia
    0.91
     Nebraska
    0.88
     Sioux
    0.87
    sie
    0.86
     Wyoming
    0.85
     Idaho
    0.85
     Rapids
    0.85
    Bone
    0.79
    Activations Density 0.101%

    No Known Activations