© 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. 3675
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and software tools

    oai_token-act-pair · gpt-3.5-turbo

    specific terms and concepts associated with various types of media, technology, and cultural references

    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
    ayers
    -0.78
    inders
    -0.74
    actionDate
    -0.71
    erity
    -0.70
    ouls
    -0.70
    aspers
    -0.70
    avers
    -0.70
    ravings
    -0.69
    acs
    -0.69
    ij
    -0.68
    POSITIVE LOGITS
     represents
    1.21
     resembles
    1.20
     replaces
    1.17
     corresponds
    1.17
     differs
    1.16
     consists
    1.15
     derives
    1.13
     incorporates
    1.12
     appears
    1.12
     contains
    1.11
    Activations Density 0.351%

    No Known Activations