© 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. 10080
    Prev
    Next
    INDEX
    Explanations

    names of political figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    entities and roles related to individuals in a news context

    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
     respect
    -0.73
    DragonMagazine
    -0.62
     craving
    -0.59
     persecut
    -0.57
     aim
    -0.57
    Issue
    -0.57
     privile
    -0.57
     disproportion
    -0.56
     counterfeit
    -0.56
    .):
    -0.56
    POSITIVE LOGITS
     told
    1.38
     tells
    1.19
    told
    1.19
     wrote
    1.17
     said
    1.08
    wrote
    1.04
    said
    0.99
     explained
    0.97
     tweeted
    0.96
     remarked
    0.91
    Activations Density 0.159%

    No Known Activations