© 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. 10-RES-JB
    11. 2698
    Prev
    Next
    INDEX
    Explanations

    phrases related to resources, tools, and means needed for various purposes such as law enforcement, protection, identification, and informing

    oai_token-act-pair · gpt-3.5-turbo

    references to tools and resources related to security and enforcement

    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
    itled
    -0.70
     boo
    -0.68
    roth
    -0.67
    roma
    -0.67
    holiday
    -0.63
    vertisement
    -0.62
    livion
    -0.62
     festivities
    -0.61
    pered
    -0.61
     Parables
    -0.61
    POSITIVE LOGITS
     available
    1.06
     expertise
    1.04
     capabilities
    1.02
     tools
    1.02
    available
    1.02
     mobilized
    1.02
     resources
    0.99
     trained
    0.99
     arsenal
    0.97
     capability
    0.97
    Activations Density 0.356%

    No Known Activations