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. 16075
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various locations and names

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of the word "aver" in various contexts

    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
     traffic
    -0.67
     Audi
    -0.66
     hex
    -0.64
     Fo
    -0.64
     security
    -0.61
     Psy
    -0.61
     bits
    -0.59
     Nordic
    -0.59
     Nikki
    -0.59
     fo
    -0.59
    POSITIVE LOGITS
    aver
    4.72
    avers
    3.22
    aving
    1.51
    aves
    1.39
    ave
    1.35
    aved
    1.24
    avery
    1.17
    avering
    1.16
    aven
    1.15
    av
    1.10
    Activations Density 0.013%

    No Known Activations