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. 7933
    Prev
    Next
    INDEX
    Explanations

    the word "there" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "there" and its variations in context

    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
     Throne
    -0.72
     Ashes
    -0.67
     Slayer
    -0.61
     Coffin
    -0.59
     Doom
    -0.57
     Dise
    -0.57
    ship
    -0.57
     Armored
    -0.56
    HAM
    -0.55
     Toast
    -0.54
    POSITIVE LOGITS
    abouts
    1.48
    upon
    1.16
    after
    0.99
     are
    0.90
    etheless
    0.85
    fore
    0.85
    currently
    0.85
     were
    0.85
     weren
    0.83
    FORE
    0.80
    Activations Density 0.118%

    No Known Activations