© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13925
    Prev
    Next
    INDEX
    Explanations

    instances of expressing hypothetical situations or regrets

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing hypothetical situations and the consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.64
    iaz
    -0.61
     ¶
    -0.57
     haunt
    -0.56
    Activ
    -0.54
    ishable
    -0.54
    bridge
    -0.54
    âĨij
    -0.54
     reinforce
    -0.53
    rift
    -0.53
    POSITIVE LOGITS
     dreamed
    1.27
     guessed
    1.18
     survived
    1.16
     imagined
    1.16
     gotten
    1.11
     existed
    1.11
     bothered
    1.08
     arisen
    1.05
     tolerated
    1.05
     cared
    1.04
    Activations Density 0.077%

    No Known Activations