© 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. 0-RES-JB
    11. 5304
    Prev
    Next
    INDEX
    Explanations

    words related to hindrance or obstruction

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles, particularly those ending in 'ering'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Swe
    -0.57
    人
    -0.57
     universe
    -0.55
     cat
    -0.55
    ãĥŀ
    -0.55
     transports
    -0.54
     bases
    -0.54
     Nation
    -0.53
     Twist
    -0.52
     rhythm
    -0.52
    POSITIVE LOGITS
    ering
    4.58
    ered
    3.06
    erers
    2.17
    erer
    2.05
    ers
    1.59
    ery
    1.58
    erness
    1.40
    erman
    1.33
    ern
    1.33
    erc
    1.32
    Activations Density 0.010%

    No Known Activations