© 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. 5589
    Prev
    Next
    INDEX
    Explanations

    names of organizations or entities, such as companies, law firms, hospitals, or market research firms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to specific organizations or designations

    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
    taboola
    -0.84
    ItemTracker
    -0.66
     showc
    -0.63
     colorful
    -0.63
     glowing
    -0.62
    licted
    -0.61
     conspicuous
    -0.61
    alam
    -0.60
     glow
    -0.60
     recol
    -0.59
    POSITIVE LOGITS
    ATA
    1.14
    AR
    1.09
    OPS
    1.08
    OT
    1.07
    Vs
    1.03
    RA
    1.03
    TO
    1.03
    OP
    1.03
    NT
    1.02
    OSS
    1.02
    Activations Density 0.154%

    No Known Activations