© 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. 6-RES-JB
    11. 15400
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions and movements

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-informative segments in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constitu
    -0.83
    etheless
    -0.83
     destro
    -0.81
     withd
    -0.77
     exha
    -0.76
     occas
    -0.73
    opausal
    -0.72
    istically
    -0.71
     circulation
    -0.70
     confir
    -0.69
    POSITIVE LOGITS
    ings
    1.21
    Maker
    1.05
    ners
    1.03
    away
    1.00
    ables
    0.96
    ers
    0.96
    haus
    0.93
    down
    0.91
    aways
    0.91
    ments
    0.89
    Activations Density 0.198%

    No Known Activations