© 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. 11415
    Prev
    Next
    INDEX
    Explanations

    verbs that convey intentions or meanings

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the concept of meaning and intent

    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
    aqu
    -0.70
    oute
    -0.68
    Newsletter
    -0.66
    icht
    -0.66
    uries
    -0.65
    iets
    -0.64
    @#&
    -0.63
    dfx
    -0.63
    anon
    -0.62
    itations
    -0.62
    POSITIVE LOGITS
     goodbye
    0.96
     something
    0.91
     nothing
    0.85
     anything
    0.79
     bye
    0.78
     spirited
    0.77
     exactly
    0.76
    lessness
    0.75
    piece
    0.72
     differently
    0.69
    Activations Density 0.044%

    No Known Activations