© 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. 0-RES-JB
    11. 466
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is being advised not to put effort into something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bother" and its variations

    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
    AG
    -0.62
    ifter
    -0.59
     Ending
    -0.57
     Designs
    -0.56
     representing
    -0.54
    cell
    -0.54
     Blueprint
    -0.54
     styled
    -0.54
    ments
    -0.53
    robe
    -0.53
    POSITIVE LOGITS
     bother
    3.79
     bothering
    2.42
     bothered
    2.31
     bothers
    2.15
     hassle
    1.48
     worry
    1.35
     inconvenience
    1.32
     annoy
    1.21
     trouble
    1.21
     annoyance
    1.15
    Activations Density 0.008%

    No Known Activations