Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24250
    Prev
    Next
    INDEX
    Explanations

    words related to efficiency and convenience in terms of avoiding or simplifying tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to efficiency and saving effort or resources

    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
    aez
    -0.80
    positive
    -0.76
     Pigs
    -0.72
    neutral
    -0.68
    eden
    -0.65
    isSpecialOrderable
    -0.63
     Positive
    -0.63
    ACTED
    -0.62
     )]
    -0.61
     indications
    -0.61
    POSITIVE LOGITS
     cumbersome
    1.26
     costly
    1.21
     hassle
    1.15
     tedious
    1.12
     unnecessarily
    1.11
     manually
    1.07
     expensive
    1.05
     lengthy
    0.97
     bulky
    0.96
     fuss
    0.94
    Activations Density 0.451%

    No Known Activations