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. 0-RES-JB
    6. 17297
    Prev
    Next
    INDEX
    Explanations

    words related to specific topic areas or subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to topics related to a specific subject matter or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marsh
    -0.77
     pasture
    -0.75
     Vers
    -0.71
     grass
    -0.69
     beck
    -0.66
     sunlight
    -0.66
     Opt
    -0.66
     ball
    -0.65
     balls
    -0.65
     hope
    -0.65
    POSITIVE LOGITS
    related
    3.65
    associated
    1.96
     related
    1.93
    Related
    1.80
    specific
    1.78
     Related
    1.77
    themed
    1.68
    relevant
    1.67
    linked
    1.55
    involved
    1.51
    Activations Density 0.022%

    No Known Activations