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. 10731
    Prev
    Next
    INDEX
    Explanations

    phrases related to outcomes surpassing others

    oai_token-act-pair · gpt-3.5-turbo

    the term "out" in various contexts indicating superiority or surpassing

    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
     Provision
    -0.69
     Shack
    -0.65
     horizont
    -0.64
     counselling
    -0.64
     Torrent
    -0.64
     Alley
    -0.60
     Guid
    -0.58
     Revolutionary
    -0.58
     advisory
    -0.57
     Bad
    -0.57
    POSITIVE LOGITS
    wrote
    1.21
    poses
    1.14
    ifies
    1.12
    sell
    1.11
    etheless
    1.04
    ends
    1.02
    comes
    1.00
    produ
    0.98
    did
    0.95
    rouse
    0.94
    Activations Density 0.142%

    No Known Activations