© 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. 2511
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific activities or objects

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation and related content

    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
     affili
    -0.97
     contingency
    -0.93
     tremend
    -0.89
     cessation
    -0.89
     attrition
    -0.87
     challeng
    -0.85
     reconc
    -0.82
     cohesion
    -0.82
     commitments
    -0.81
    ŃĶ
    -0.80
    POSITIVE LOGITS
     Researchers
    1.24
    SPONSORED
    1.23
    Enlarge
    1.17
     Officials
    1.16
     Scientists
    1.16
    Researchers
    1.14
     Experts
    1.14
     Photographer
    1.13
     Critics
    1.12
     Customers
    1.11
    Activations Density 0.458%

    No Known Activations