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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 20151
    Prev
    Next
    INDEX
    Explanations

    phrases related to various types of work, projects, and funding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of work, production, and infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.74
    ovie
    -0.72
     salute
    -0.67
    erker
    -0.66
    esson
    -0.61
    mma
    -0.59
    ilet
    -0.59
    ochet
    -0.59
    ammad
    -0.58
     ______
    -0.58
    POSITIVE LOGITS
     continues
    1.14
     tends
    1.12
     has
    1.11
     remains
    1.09
     hasn
    1.07
     varies
    1.05
     is
    1.01
     was
    1.00
     persists
    1.00
     exists
    1.00
    Activations Density 0.310%

    No Known Activations