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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 7491
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, policies, and political actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "has" to indicate possession or existence in various contexts

    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
     Incarn
    -0.70
     writes
    -0.70
     knows
    -0.69
    acle
    -0.64
    bery
    -0.63
    remember
    -0.61
     remembers
    -0.60
    know
    -0.60
     divorce
    -0.60
     Desc
    -0.59
    POSITIVE LOGITS
     garnered
    1.11
     been
    1.11
     sparked
    1.07
     resulted
    1.07
     attracted
    1.04
     prompted
    0.98
     angered
    0.98
     netted
    0.97
     provoked
    0.96
    been
    0.96
    Activations Density 0.131%

    No Known Activations