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. 8-RES-JB
    6. 19688
    Prev
    Next
    INDEX
    Explanations

    phrases related to things that come with certain conditions or attributes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate conditions or requirements associated with something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Discuss
    -0.72
    chan
    -0.70
    antis
    -0.69
    atism
    -0.69
    eric
    -0.67
    ouf
    -0.67
     Appears
    -0.67
    ople
    -0.64
    Fair
    -0.63
    Gamer
    -0.62
    POSITIVE LOGITS
     caveats
    0.94
     regard
    0.89
    stood
    0.88
     disclaim
    0.81
     regards
    0.79
     caveat
    0.76
     plenty
    0.75
     warranty
    0.74
     strings
    0.73
     baggage
    0.73
    Activations Density 0.076%

    No Known Activations