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. 8-RES-JB
    6. 21961
    Prev
    Next
    INDEX
    Explanations

    words related to improvements and advancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to risk and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    president
    -0.66
    inav
    -0.64
     (£
    -0.62
    town
    -0.61
     Vance
    -0.59
    ylum
    -0.59
    last
    -0.59
     Maryland
    -0.59
    Facebook
    -0.59
    ador
    -0.58
    POSITIVE LOGITS
     cumbers
    0.97
    pmwiki
    0.91
     flexibility
    0.85
     tremend
    0.83
     inefficient
    0.83
     temptation
    0.82
     congestion
    0.79
     tendency
    0.79
    catentry
    0.78
    effic
    0.77
    Activations Density 0.529%

    No Known Activations