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. 12985
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a distinctive or unique feature or item

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "signature" associated with distinct attributes or features

    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
    ulu
    -0.74
    ASC
    -0.74
    aiman
    -0.74
    tics
    -0.71
    á½
    -0.70
    conom
    -0.69
    isen
    -0.68
    agan
    -0.68
    Ïī
    -0.68
    onest
    -0.68
    POSITIVE LOGITS
     signature
    0.98
    ATURE
    0.75
     breaker
    0.74
     hallmark
    0.72
    CHAT
    0.71
     signatures
    0.69
    zag
    0.68
    prints
    0.65
     engraved
    0.65
     distinctive
    0.65
    Activations Density 0.008%

    No Known Activations