© 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. 6412
    Prev
    Next
    INDEX
    Explanations

    words related to positions or statements being taken

    oai_token-act-pair · gpt-3.5-turbo

    indicators of positive actions or outcomes

    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
     snail
    -0.71
     Abu
    -0.68
     Oath
    -0.67
     mourning
    -0.66
    ãĢIJ
    -0.64
     overnight
    -0.62
     Alabama
    -0.61
     ramp
    -0.61
     DRM
    -0.60
     BF
    -0.60
    POSITIVE LOGITS
    pos
    4.31
    position
    2.05
    POS
    2.03
    posing
    1.91
    pose
    1.86
    poses
    1.71
    posed
    1.64
    posal
    1.59
    Pos
    1.55
    po
    1.38
    Activations Density 0.013%

    No Known Activations