© 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. 11-RES-JB
    11. 10107
    Prev
    Next
    INDEX
    Explanations

    names of people or characters in a biography or profile

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their educational or professional backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.77
     Causes
    -0.72
     Supp
    -0.72
    acea
    -0.70
    éĹĺ
    -0.70
     Deliver
    -0.67
     Silence
    -0.67
    ãĥķãĤ¡
    -0.67
     Customers
    -0.66
     Destroyer
    -0.65
    POSITIVE LOGITS
     graduated
    1.52
     exce
    1.52
     enrolled
    1.50
     maj
    1.43
     attended
    1.32
     studied
    1.29
     enroll
    1.21
     transitioned
    1.17
     progressed
    1.16
     grew
    1.14
    Activations Density 0.292%

    No Known Activations