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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 5757
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a contrast or exception

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "albeit" to signify contrast or concession

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

    No Comments

    Negative Logits
    ogy
    -0.74
    center
    -0.71
    asus
    -0.67
    rush
    -0.67
    McC
    -0.67
    hal
    -0.66
    aed
    -0.65
    vasive
    -0.64
    atur
    -0.64
    andr
    -0.64
    POSITIVE LOGITS
    chery
    0.95
    soever
    0.90
    ional
    0.88
     sparing
    0.87
     albeit
    0.85
     fortunately
    0.84
    tons
    0.84
     guiActiveUn
    0.81
    albeit
    0.78
     excluding
    0.77
    Activations Density 0.010%

    No Known Activations