© 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. 5289
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions with potential consequences

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social issues and advocacy

    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
    Balt
    -0.55
     advoc
    -0.51
    irs
    -0.50
    olic
    -0.50
     seiz
    -0.50
    Els
    -0.48
     lett
    -0.45
     welf
    -0.45
     haw
    -0.45
     bluff
    -0.45
    POSITIVE LOGITS
     surfaced
    0.82
     illustrates
    0.76
     violates
    0.75
     amounted
    0.75
     seemed
    0.74
     suggests
    0.73
     underscores
    0.72
    ?,
    0.72
     appeared
    0.70
     seems
    0.70
    Activations Density 1.372%

    No Known Activations