© 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. 15511
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and operations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to functionality and performance in technical contexts

    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
    ppo
    -0.65
    ãģ®éŃĶ
    -0.60
     renovated
    -0.58
     mosqu
    -0.57
    iversary
    -0.57
     photographed
    -0.56
    URRENT
    -0.54
     commemor
    -0.53
    atown
    -0.52
     commem
    -0.52
    POSITIVE LOGITS
     abound
    0.89
     etc
    0.66
     Helpful
    0.65
     discretion
    0.62
     ;)
    0.58
     include
    0.58
    both
    0.57
     yes
    0.57
    sic
    0.56
    =-
    0.56
    Activations Density 1.032%

    No Known Activations