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. 15087
    Prev
    Next
    INDEX
    Explanations

    nicknames or terms of endearment used to refer to specific individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    quotes and references within the text

    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
     grasp
    -0.83
     rall
    -0.79
     accomp
    -0.78
     vents
    -0.77
     tackle
    -0.75
     fret
    -0.75
     finish
    -0.73
     scale
    -0.73
     buoy
    -0.73
     bask
    -0.71
    POSITIVE LOGITS
    little
    1.47
    pure
    1.40
    dirty
    1.39
    dark
    1.38
    gold
    1.37
    the
    1.36
    false
    1.35
    traditional
    1.32
    moral
    1.30
    beaut
    1.30
    Activations Density 0.114%

    No Known Activations