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. 7-RES-JB
    6. 20418
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical symbols in a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to temporal or conditional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concess
    -0.50
     Lama
    -0.49
     equivalent
    -0.47
     outwe
    -0.47
     lever
    -0.47
     programmed
    -0.47
     bottleneck
    -0.46
     spearheaded
    -0.46
    abwe
    -0.46
     Jinping
    -0.45
    POSITIVE LOGITS
    OSP
    0.67
    lement
    0.65
    generic
    0.58
    gif
    0.55
    ieg
    0.54
    catentry
    0.54
    natureconservancy
    0.53
    OTOS
    0.53
    ISC
    0.53
    attery
    0.53
    Activations Density 0.646%

    No Known Activations