© 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. 7-RES-JB
    11. 20813
    Prev
    Next
    INDEX
    Explanations

    phrases related to greetings and positive affirmations

    oai_token-act-pair · gpt-3.5-turbo

    the word "Good."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptin
    -0.79
    eters
    -0.78
    hyde
    -0.70
    opers
    -0.68
     Tsukuyomi
    -0.67
    oths
    -0.66
    EStream
    -0.66
    ĸļ
    -0.66
    pora
    -0.66
    hod
    -0.65
    POSITIVE LOGITS
    enough
    1.27
    reads
    1.15
    bye
    1.15
     Samar
    1.07
     luck
    1.06
    luck
    1.03
     intentions
    0.99
    sword
    0.91
     bye
    0.91
     deed
    0.90
    Activations Density 0.074%

    No Known Activations