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. 16843
    Prev
    Next
    INDEX
    Explanations

    specific alphanumeric patterns in the text, such as 'Ċ' followed by '9', 'Ċ' followed by '10', etc

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or lists within a larger context

    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
    xual
    -0.77
     que
    -0.66
     antiv
    -0.63
     undecided
    -0.62
     emoji
    -0.61
     urges
    -0.60
     urge
    -0.60
     shot
    -0.60
     hay
    -0.59
     wraps
    -0.59
    POSITIVE LOGITS
    Eventually
    1.29
    Shortly
    1.24
    Later
    1.23
    Fortunately
    1.19
    SPONSORED
    1.19
    Then
    1.17
    Instead
    1.16
    Unfortunately
    1.16
    Initially
    1.16
    During
    1.15
    Activations Density 0.672%

    No Known Activations