© 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. 5396
    Prev
    Next
    INDEX
    Explanations

    phrases related to things that have the potential to happen or be achieved

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potentiality or possibility

    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
    english
    -0.70
     english
    -0.68
    noon
    -0.68
    winter
    -0.64
    uph
    -0.63
    Newsletter
    -0.63
    gat
    -0.62
    blogspot
    -0.62
     Prayer
    -0.62
     till
    -0.62
    POSITIVE LOGITS
     potentially
    3.28
     possibly
    1.98
     potential
    1.81
     theoretically
    1.63
    possibly
    1.58
     presumably
    1.37
     Potential
    1.32
     arguably
    1.32
    ivably
    1.29
     likely
    1.27
    Activations Density 0.012%

    No Known Activations