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. 6-RES-JB
    6. 4834
    Prev
    Next
    INDEX
    Explanations

    words related to the establishment or creation of entities, systems, or agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the initiation or formation of systems, institutions, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sb
    -0.69
     bra
    -0.62
     Zip
    -0.62
     Yelp
    -0.59
    INO
    -0.58
    akia
    -0.58
    ymm
    -0.58
     sqor
    -0.56
    ortium
    -0.56
    lette
    -0.55
    POSITIVE LOGITS
     thereof
    0.95
     of
    0.81
    ieth
    0.75
     process
    0.74
    ghai
    0.71
    itial
    0.69
     OF
    0.68
    ablishment
    0.67
    athering
    0.67
    ãĥĭ
    0.66
    Activations Density 0.240%

    No Known Activations