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. 9-RES-JB
    6. 18974
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating similarity or resemblance

    oai_token-act-pair · gpt-3.5-turbo

    references to things that are reminiscent or bear resemblance to other concepts or styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gression
    -0.77
    foreseen
    -0.73
    priority
    -0.71
     unanswered
    -0.69
    icals
    -0.67
     delayed
    -0.67
    rer
    -0.66
     Ended
    -0.65
    verning
    -0.65
    ticket
    -0.65
    POSITIVE LOGITS
     reminiscent
    1.08
     resemblance
    1.00
     resemb
    0.99
     likeness
    0.96
     akin
    0.94
     resemble
    0.92
     resembles
    0.91
     Gothic
    0.88
     resembling
    0.87
    gypt
    0.82
    Activations Density 0.411%

    No Known Activations