© 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. 16502
    Prev
    Next
    INDEX
    Explanations

    organization names and titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The" and its variations, indicating a focus on specific introductory phrases or statements

    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
    APD
    -0.87
    ghazi
    -0.81
    20439
    -0.74
     elsewhere
    -0.74
    ratom
    -0.73
    still
    -0.71
    NetMessage
    -0.70
     Certainly
    -0.70
    Lago
    -0.70
    abuse
    -0.70
    POSITIVE LOGITS
     goal
    1.50
     aim
    1.39
     purpose
    1.25
     result
    1.23
     premise
    1.22
     centerpiece
    1.21
     idea
    1.21
     objective
    1.18
     gist
    1.16
     motto
    1.13
    Activations Density 0.309%

    No Known Activations