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. 6-RES-JB
    6. 9128
    Prev
    Next
    INDEX
    Explanations

    the word "are" at the tenth position

    oai_token-act-pair · gpt-3.5-turbo

    the verb "are" and its contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urry
    -0.70
    uld
    -0.70
    onso
    -0.70
    iates
    -0.69
    ossom
    -0.66
    dom
    -0.64
    town
    -0.64
    speak
    -0.63
    poke
    -0.62
    osate
    -0.62
    POSITIVE LOGITS
    senal
    1.25
    wolves
    0.98
     supposed
    0.96
     hereby
    0.93
     currently
    0.91
     not
    0.87
     usually
    0.85
     unlikely
    0.85
     intimately
    0.85
     presently
    0.85
    Activations Density 0.353%

    No Known Activations