© 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. 11547
    Prev
    Next
    INDEX
    Explanations

    words related to specific fields like environment, cybersecurity, economics, government, ethics, wildlife, defense, human rights, security, and law

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various sectors, particularly environmental, cybersecurity, and social issues

    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
     ç¥ŀ
    -0.84
     Converted
    -0.73
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.70
    chens
    -0.66
    ushima
    -0.66
    kson
    -0.66
     Himself
    -0.66
     (>
    -0.65
    heimer
    -0.64
     Candidate
    -0.63
    POSITIVE LOGITS
     analyst
    1.25
     bureau
    1.19
     experts
    1.18
     advisory
    1.14
     adviser
    1.13
     researcher
    1.10
     specialist
    1.10
     analysts
    1.09
     expert
    1.09
     historian
    1.08
    Activations Density 0.309%

    No Known Activations