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. 19851
    Prev
    Next
    INDEX
    Explanations

    numbers in a specific format, such as dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and financial amounts

    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
     crunch
    -0.69
    osexual
    -0.61
     sides
    -0.61
     necks
    -0.59
    ftime
    -0.58
     companion
    -0.58
     footing
    -0.57
     Cyrus
    -0.57
     behavioural
    -0.56
     preservation
    -0.56
    POSITIVE LOGITS
    MSN
    1.07
    éĹĺ
    0.87
    000
    0.86
    627
    0.84
    968
    0.84
    368
    0.81
    616
    0.80
    685
    0.80
    ãĥ´ãĤ¡
    0.80
    660
    0.79
    Activations Density 0.210%

    No Known Activations