© 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. 9-RES-JB
    11. 16388
    Prev
    Next
    INDEX
    Explanations

    information related to distribution and promotion, particularly in reaching different audiences and ensuring content is available to the public

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to public access and community engagement

    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
    wcsstore
    -0.69
    natureconservancy
    -0.68
    bard
    -0.68
    illac
    -0.61
    assian
    -0.60
    Fat
    -0.60
    zilla
    -0.60
    inventoryQuantity
    -0.60
    icut
    -0.60
    agate
    -0.59
    POSITIVE LOGITS
     viewers
    1.96
     listeners
    1.94
     audiences
    1.88
     readers
    1.86
     consumers
    1.66
     voters
    1.59
     attendees
    1.57
     audience
    1.56
     subscribers
    1.53
     customers
    1.49
    Activations Density 1.694%

    No Known Activations