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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11803
    Prev
    Next
    INDEX
    Explanations

    web URLs and software code snippets

    oai_token-act-pair · gpt-3.5-turbo

    web-related or technical elements, particularly URLs, references, and specific parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iland
    -0.61
     conclud
    -0.61
    yip
    -0.56
    idis
    -0.56
    achev
    -0.55
    \-
    -0.53
    oric
    -0.53
     Samoa
    -0.53
    idays
    -0.53
    uddin
    -0.52
    POSITIVE LOGITS
    taboola
    0.75
    ħĭ
    0.60
     ACTIONS
    0.57
     Soup
    0.56
    undrum
    0.55
    */(
    0.54
     Partnership
    0.53
     Truth
    0.53
     ³³
    0.52
     Invalid
    0.52
    Activations Density 1.534%

    No Known Activations