© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 17627
    Prev
    Next
    INDEX
    Explanations

    text indicating the creation of handmade objects

    oai_token-act-pair · gpt-3.5-turbo

    references to handcrafted or produced objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yet
    -0.82
     ILCS
    -0.81
    feat
    -0.73
     guiName
    -0.73
    é»Ĵ
    -0.73
    vre
    -0.69
    atican
    -0.67
     Tanz
    -0.67
    soDeliveryDate
    -0.66
    )",
    -0.65
    POSITIVE LOGITS
     depleted
    0.66
     enriched
    0.66
     sap
    0.65
    selection
    0.63
     outcome
    0.62
     Pigs
    0.60
     Ple
    0.60
     recess
    0.60
     depletion
    0.59
     Administ
    0.59
    Activations Density 0.000%

    No Known Activations