© 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. 7-RES-JB
    11. 23127
    Prev
    Next
    INDEX
    Explanations

    references to specific groups of people or professionals

    oai_token-act-pair · gpt-3.5-turbo

    the word "who" and related phrases indicating subjects in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BACK
    -0.86
    Untitled
    -0.78
     VIDEOS
    -0.76
     Delicious
    -0.75
     Anything
    -0.74
    SE
    -0.73
    CAST
    -0.67
    å½
    -0.67
     Affordable
    -0.63
    UT
    -0.63
    POSITIVE LOGITS
     migrated
    0.96
    oping
    0.92
     comprise
    0.91
    umbnails
    0.88
     resided
    0.87
    oped
    0.86
    upon
    0.84
    izens
    0.84
     fled
    0.83
     specialize
    0.83
    Activations Density 0.145%

    No Known Activations