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

    Neuronpedia

    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. 10-RES-JB
    11. 13924
    Prev
    Next
    INDEX
    Explanations

    instances where the subject is reflecting on past experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal reflections and self-references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unfocusedRange
    -0.62
     preserves
    -0.62
     winners
    -0.60
     endif
    -0.59
    orate
    -0.58
    Regardless
    -0.58
    ãĤ¼
    -0.58
     applause
    -0.56
     abdom
    -0.56
     none
    -0.56
    POSITIVE LOGITS
    'm
    1.19
    've
    0.98
     arrived
    0.92
     started
    0.91
     asked
    0.87
     interviewed
    0.87
     myself
    0.87
     woke
    0.86
     first
    0.84
     hear
    0.83
    Activations Density 0.079%

    No Known Activations