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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 849
    Prev
    Next
    INDEX
    Explanations

    the word 'worried' or variations of it

    oai_token-act-pair · gpt-4-turbo

    situations or contexts where worry or concern is expressed

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or anxiety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.90
    inters
    -0.84
    guided
    -0.77
    animate
    -0.74
    ending
    -0.73
    change
    -0.72
    ractions
    -0.72
    adr
    -0.71
    edited
    -0.71
    asters
    -0.71
    POSITIVE LOGITS
     worried
    0.97
     citiz
    0.87
     worry
    0.79
     afraid
    0.77
     adolesc
    0.77
     fret
    0.76
     schizophren
    0.75
     bells
    0.74
     overe
    0.72
     worrying
    0.71
    Activations Density 0.014%

    No Known Activations