© 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. 5877
    Prev
    Next
    INDEX
    Explanations

    information related to business dealings or agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to community agreements and financial contributions or initiatives

    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
     ('
    -0.92
     whilst
    -0.87
    âĢIJ
    -0.87
    ".[
    -0.86
     Whilst
    -0.84
    ';
    -0.81
     [âĢ¦]
    -0.79
     (@
    -0.78
     âĪ¼
    -0.78
     ',
    -0.78
    POSITIVE LOGITS
     statewide
    1.02
    atown
    0.89
     counselors
    0.86
     nonprofits
    0.85
     downtown
    0.85
     motorists
    0.84
     homeowners
    0.84
     sheriff
    0.83
     crews
    0.83
     signage
    0.82
    Activations Density 1.605%

    No Known Activations