© 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. 10034
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to intense or impactful situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "nailing" in various 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
    REDACTED
    -0.81
    =-=-=-=-=-=-=-=-
    -0.71
    overe
    -0.71
    inventoryQuantity
    -0.71
    Æ
    -0.70
    entric
    -0.70
     Reserved
    -0.70
    ioch
    -0.69
    doi
    -0.69
    iew
    -0.69
    POSITIVE LOGITS
     polish
    1.19
     biting
    0.98
     salon
    0.97
     nail
    0.96
     coffin
    0.95
     nails
    0.89
     fungus
    0.88
    picking
    0.86
    bone
    0.76
     hammered
    0.76
    Activations Density 0.061%

    No Known Activations