© 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. 8-RES-JB
    11. 16726
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations or judgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant events or rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Versions
    -0.84
    books
    -0.76
    runs
    -0.72
    mins
    -0.72
    enery
    -0.70
     outfits
    -0.70
     skirts
    -0.68
    itely
    -0.66
    units
    -0.66
    models
    -0.66
    POSITIVE LOGITS
     reminder
    1.24
     culmination
    1.15
     testament
    1.11
     deterrent
    1.11
     boon
    1.11
     setback
    1.08
     cornerstone
    1.07
     milestone
    1.07
     continuation
    1.06
     reflection
    1.05
    Activations Density 0.266%

    No Known Activations