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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 7029
    Prev
    Next
    INDEX
    Explanations

    numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    isolated numeric tokens or sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     administr
    -0.64
    holding
    -0.56
     tomorrow
    -0.54
    went
    -0.54
    lier
    -0.53
    rium
    -0.52
     meanwhile
    -0.52
     worry
    -0.52
    stood
    -0.52
    urally
    -0.52
    POSITIVE LOGITS
     SHARES
    1.16
     Shares
    1.02
     Pages
    0.98
     Explicit
    0.96
     stitches
    0.88
     Reasons
    0.87
     Reviews
    0.83
     Views
    0.81
     Comments
    0.80
     Votes
    0.78
    Activations Density 0.086%

    No Known Activations