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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22486
    Prev
    Next
    INDEX
    Explanations

    financial terms and values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "This" or phrases indicating specific references or quantities

    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
    aws
    -0.74
    respons
    -0.68
    velop
    -0.68
    icons
    -0.66
    aths
    -0.65
    Delivery
    -0.64
    isms
    -0.63
    pots
    -0.62
    doms
    -0.62
    bell
    -0.62
    POSITIVE LOGITS
     latter
    1.15
     resulted
    1.08
     ensures
    0.92
     corresponds
    0.92
     culminated
    0.92
     allows
    0.91
     enables
    0.91
     consisted
    0.87
     eliminates
    0.84
     includes
    0.84
    Activations Density 0.205%

    No Known Activations