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. 9-RES-JB
    6. 11016
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computing such as files, actions, responses, crashes, and connections

    oai_token-act-pair · gpt-3.5-turbo

    references to files and data management processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.78
    addon
    -0.62
    Ire
    -0.61
    Joined
    -0.59
     Damn
    -0.58
    yet
    -0.58
     bullish
    -0.57
    Mos
    -0.57
    Thanks
    -0.56
    RIP
    -0.56
    POSITIVE LOGITS
     tends
    1.48
     becomes
    1.45
     consists
    1.44
     depends
    1.43
     must
    1.39
     determines
    1.37
     varies
    1.33
     may
    1.31
     disappears
    1.29
     corresponds
    1.29
    Activations Density 0.605%

    No Known Activations