Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16459
    Prev
    Next
    INDEX
    Explanations

    phrases related to the creation or establishment of something

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the establishment and creation of systems, organizations, or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sb
    -0.65
     bra
    -0.64
     Yelp
    -0.63
    ortium
    -0.63
    akia
    -0.63
    ussen
    -0.63
     Zip
    -0.63
    lette
    -0.61
    heddar
    -0.59
     Ox
    -0.57
    POSITIVE LOGITS
     thereof
    0.92
    ieth
    0.71
    DOWN
    0.71
     of
    0.70
     process
    0.70
    adle
    0.67
    ãĥĭ
    0.67
    Preview
    0.65
    ilitation
    0.65
    athering
    0.64
    Activations Density 0.270%

    No Known Activations