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. 4-RES-JB
    6. 18801
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical processes or calculations

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or list structures

    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
    ¬¼
    -0.71
     crunch
    -0.65
    jit
    -0.63
     hog
    -0.63
    erville
    -0.62
    eni
    -0.62
     joke
    -0.61
    ensical
    -0.60
    robe
    -0.60
    rou
    -0.59
    POSITIVE LOGITS
     respectively
    1.26
     namely
    1.24
     etc
    1.16
     whereas
    1.11
     thereby
    1.11
     preferably
    1.10
     wherein
    1.07
     whereby
    1.05
     including
    1.03
     ie
    1.01
    Activations Density 0.948%

    No Known Activations