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. 21173
    Prev
    Next
    INDEX
    Explanations

    phrases transitioning to a new topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the conjunction "and" used to connect multiple statements or ideas

    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
    fell
    -0.76
    url
    -0.67
    sk
    -0.67
    atical
    -0.66
    lde
    -0.65
    ses
    -0.65
    pees
    -0.64
    ãģĨ
    -0.64
    steam
    -0.64
    viation
    -0.61
    POSITIVE LOGITS
    romeda
    1.16
    rea
    1.04
     furthermore
    1.03
    hra
    0.97
     secondly
    0.93
     moreover
    0.89
    rogens
    0.87
    alus
    0.86
    ersen
    0.84
     consequently
    0.84
    Activations Density 0.072%

    No Known Activations