© 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. 16325
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and standards

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to corporate responsibility and community engagement

    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
    ording
    -0.76
    icter
    -0.75
    Spoiler
    -0.73
    unker
    -0.71
    riots
    -0.70
    puff
    -0.68
    trump
    -0.68
     bothered
    -0.68
    rez
    -0.67
    kan
    -0.67
    POSITIVE LOGITS
     vision
    1.13
     commitment
    1.13
     mission
    1.12
     portfolio
    1.11
     roadmap
    1.05
     products
    1.02
     partnerships
    1.01
     strengths
    1.01
     offerings
    0.99
     core
    0.99
    Activations Density 0.261%

    No Known Activations