© 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. 17074
    Prev
    Next
    INDEX
    Explanations

    special skills or qualities related to a profession or task

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with both artistic creativity and practical applications

    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
    anmar
    -0.71
     helicop
    -0.64
     metic
    -0.64
    pol
    -0.62
     vet
    -0.62
    DeliveryDate
    -0.59
    «
    -0.58
     Raw
    -0.58
     BG
    -0.58
    ãĤ¨ãĥ«
    -0.57
    POSITIVE LOGITS
    and
    0.75
     partName
    0.70
    \">
    0.66
     defe
    0.64
    \\
    0.62
    Õ
    0.61
    ally
    0.60
     isEnabled
    0.59
    &
    0.57
     and
    0.57
    Activations Density 0.166%

    No Known Activations