© 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. 9-RES-JB
    11. 3004
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth, introspection, and self-reflection

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idates
    -0.68
     themselves
    -0.61
    Their
    -0.61
     apiece
    -0.61
    ãħĭ
    -0.60
    They
    -0.59
    eds
    -0.59
    ãħĭãħĭ
    -0.51
     yourselves
    -0.51
    Lot
    -0.51
    POSITIVE LOGITS
     myself
    1.93
     my
    1.37
    My
    0.87
     My
    0.85
     MY
    0.84
    my
    0.82
     ourselves
    0.79
     am
    0.77
     personally
    0.71
     blogging
    0.70
    Activations Density 1.255%

    No Known Activations