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. 2-RES-JB
    6. 19982
    Prev
    Next
    INDEX
    Explanations

    keywords related to technological advancements and concepts like memory assistance, living computers, and digital technologies

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to medical or health-related conditions and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     �
    -0.75
     Grayson
    -0.65
     Leilan
    -0.58
     --------
    -0.57
     Cheong
    -0.57
     IU
    -0.55
    +.
    -0.54
     KR
    -0.54
    ÄŁ
    -0.53
     §§
    -0.53
    POSITIVE LOGITS
    ").
    1.47
    "),
    1.47
    ")
    1.46
    %"
    1.40
    "
    1.35
    ",
    1.32
    "],
    1.32
    )",
    1.29
    "?
    1.27
    "]
    1.26
    Activations Density 0.963%

    No Known Activations