© 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. 7561
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands, products, or well-known entities

    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
     respectively
    -0.94
     thereof
    -0.75
     meas
    -0.75
     beforehand
    -0.69
    )."
    -0.69
    SPONSORED
    -0.69
     controlling
    -0.69
    ]."
    -0.68
     ..."
    -0.67
     indistinguishable
    -0.65
    POSITIVE LOGITS
     âĵĺ
    1.28
     Profile
    1.18
    ':
    0.88
    iasis
    0.84
    !:
    0.84
    itars
    0.83
     Originally
    0.76
     Edit
    0.74
    asma
    0.72
    utsu
    0.72
    Activations Density 0.665%

    No Known Activations