© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9466
    Prev
    Next
    INDEX
    Explanations

    specific font styles and approaches related to text and design

    oai_token-act-pair · gpt-3.5-turbo

    references to different design styles or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abraham
    -0.72
    minster
    -0.68
     Mald
    -0.68
    riel
    -0.67
     Labor
    -0.66
     Cowboys
    -0.66
     Vacc
    -0.66
     Wake
    -0.65
    ×Ļ
    -0.65
     Benjamin
    -0.64
    POSITIVE LOGITS
    heet
    1.40
    styles
    1.38
     styles
    1.14
    etter
    0.96
    hops
    0.94
    ologies
    0.94
     Styles
    0.90
    uggest
    0.90
    hirt
    0.89
    hots
    0.88
    Activations Density 0.009%

    No Known Activations