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. 9-RES-JB
    6. 7803
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and technical terms related to data and computing

    oai_token-act-pair · gpt-3.5-turbo

    acronyms, abbreviations, and specific codes related to various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    want
    -0.81
    had
    -0.73
    flies
    -0.71
    chester
    -0.71
    ç
    -0.69
    taboola
    -0.69
    vim
    -0.68
    folk
    -0.68
    kar
    -0.68
    amy
    -0.67
    POSITIVE LOGITS
     compliant
    0.86
    Ds
    0.81
    s
    0.78
     holders
    0.78
    Vs
    0.76
     certification
    0.73
     bucket
    0.72
    OPS
    0.72
     specification
    0.71
     Implementation
    0.71
    Activations Density 0.232%

    No Known Activations