© 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. 4-RES-JB
    11. 7329
    Prev
    Next
    INDEX
    Explanations

    texts emphasizing the central or most important aspect

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating primary focus or purpose

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

    No Comments

    Negative Logits
     Chaser
    -0.71
    Afee
    -0.70
    anth
    -0.68
     Mann
    -0.68
    Lyn
    -0.67
     Oaks
    -0.65
    iry
    -0.63
     Isles
    -0.62
    uli
    -0.61
    wal
    -0.61
    POSITIVE LOGITS
     aimed
    0.91
     concentrated
    0.91
     focused
    0.90
     reliant
    0.88
     consist
    0.85
     geared
    0.84
     relying
    0.84
    xual
    0.83
     rely
    0.83
     comprised
    0.81
    Activations Density 0.016%

    No Known Activations