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. 4-RES-JB
    6. 17726
    Prev
    Next
    INDEX
    Explanations

    terms relating to technical fields, such as optics, bioinformatics, systems, and more

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various scientific disciplines and concepts

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

    No Comments

    Negative Logits
    yond
    -0.72
    isher
    -0.65
    ishable
    -0.64
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.63
    acters
    -0.62
    get
    -0.62
    ATTLE
    -0.62
    cooked
    -0.62
    ishers
    -0.61
    ership
    -0.61
    POSITIVE LOGITS
    ilver
    1.21
    pace
    1.19
    mith
    1.14
    uits
    1.00
    cape
    0.91
    henko
    0.91
    hots
    0.90
    ensitive
    0.90
    cript
    0.90
    ystem
    0.89
    Activations Density 0.030%

    No Known Activations