© 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. 11-RES-JB
    11. 18647
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing services or support

    oai_token-act-pair · gpt-3.5-turbo

    references to the provision of important services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rebell
    -0.78
    older
    -0.73
    abouts
    -0.72
    umblr
    -0.71
    sbm
    -0.67
    aten
    -0.64
    ickle
    -0.64
    ixties
    -0.64
     Nanto
    -0.62
     Decay
    -0.59
    POSITIVE LOGITS
     fodder
    1.16
     assistance
    1.14
     insight
    1.07
     guidance
    1.06
     sust
    1.05
     services
    1.03
     support
    1.03
     assurance
    1.00
     relief
    0.99
     protection
    0.98
    Activations Density 0.188%

    No Known Activations