© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14592
    Prev
    Next
    INDEX
    Explanations

    phrases related to drawing conclusions or making inferences based on information provided

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reasoning and drawing conclusions

    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
     infiltrated
    -0.72
     disrupted
    -0.72
     destro
    -0.66
    ggles
    -0.64
     indu
    -0.64
     frontline
    -0.63
    meet
    -0.62
    covered
    -0.60
     interrupts
    -0.60
    interrupted
    -0.59
    POSITIVE LOGITS
     conclusions
    1.17
     extrap
    1.03
     conclusion
    1.02
     conjecture
    0.98
     inference
    0.94
     conject
    0.86
     assumption
    0.86
     Conclusion
    0.86
     assuming
    0.86
    argument
    0.85
    Activations Density 0.342%

    No Known Activations