© 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. 10-RES-JB
    11. 13685
    Prev
    Next
    INDEX
    Explanations

    proper nouns representing individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing individuals and their identities or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Checking
    -0.76
    Plus
    -0.70
    hent
    -0.69
     Saying
    -0.67
     Watching
    -0.66
     Caller
    -0.65
    detail
    -0.65
    Kin
    -0.64
    UME
    -0.64
    etting
    -0.63
    POSITIVE LOGITS
     specializes
    1.40
     pioneered
    1.15
     flourished
    1.08
     oversaw
    1.08
     fought
    1.07
     thri
    1.07
     overcame
    1.06
     migrated
    1.06
     grew
    1.05
     died
    1.05
    Activations Density 0.123%

    No Known Activations