© 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. 22589
    Prev
    Next
    INDEX
    Explanations

    references to understanding or being aware of specific information, especially related to laws, technology, or social issues

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to legislative knowledge and understanding of risks associated with various situations

    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
     Sundays
    -0.59
     Schwar
    -0.58
    luck
    -0.55
    aturdays
    -0.55
    anus
    -0.55
    grand
    -0.55
     reunion
    -0.54
     Marino
    -0.54
     Flore
    -0.52
    orian
    -0.52
    POSITIVE LOGITS
     pitfalls
    1.00
     nuances
    0.99
     risks
    0.96
     realities
    0.92
     impacts
    0.91
     misconceptions
    0.80
     issues
    0.80
     differently
    0.79
     cues
    0.78
     responsibly
    0.78
    Activations Density 0.561%

    No Known Activations