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. 4-RES-JB
    6. 3600
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or mentioning a topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing discussion or conversation about a topic

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

    No Comments

    Negative Logits
    emale
    -0.81
    iverpool
    -0.79
    \/\/
    -0.77
    eele
    -0.74
    uala
    -0.71
    Insp
    -0.70
    avorite
    -0.70
    chance
    -0.69
    peria
    -0.69
    quez
    -0.67
    POSITIVE LOGITS
     aloud
    0.88
     loudly
    0.88
     louder
    0.86
     about
    0.75
    bone
    0.73
    ebus
    0.70
    ij士
    0.70
     drums
    0.69
     voices
    0.69
     frankly
    0.68
    Activations Density 0.021%

    No Known Activations