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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9210
    Prev
    Next
    INDEX
    Explanations

    uniquely spelled names or titles

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns associated with individuals and organizations

    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
    Els
    -0.71
    orage
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.69
    sexual
    -0.64
    ATER
    -0.64
     Adin
    -0.64
    PASS
    -0.62
    Load
    -0.62
    ASE
    -0.61
    yond
    -0.61
    POSITIVE LOGITS
     congratulated
    1.10
     famously
    1.09
     remarked
    1.08
     assures
    1.07
     agrees
    1.05
     acknowledges
    1.04
     commented
    1.04
     understands
    1.03
     joked
    1.03
     insists
    1.03
    Activations Density 0.419%

    No Known Activations