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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 419
    Prev
    Next
    INDEX
    Explanations

    words that convey positivity or enhancement

    oai_token-act-pair · gpt-4-turbo

    terms related to different types of media production and filming techniques

    oai_token-act-pair · gpt-3.5-turbo

    mentions of personal experiences and perspectives related to art, creativity, and subjective impacts

    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
     âĢº
    -0.58
    photos
    -0.52
    ĵĺ
    -0.51
    ãĥ©ãĥ³
    -0.49
     HuffPost
    -0.49
    -0.48
     Aram
    -0.48
    WAR
    -0.47
    mx
    -0.45
     FedEx
    -0.45
    POSITIVE LOGITS
    ebted
    0.55
    opted
    0.54
     rul
    0.51
    hower
    0.51
     unworthy
    0.47
    unia
    0.46
    determination
    0.46
     condem
    0.45
    eteria
    0.45
    onga
    0.45
    Activations Density 4.055%

    No Known Activations