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

    Neuronpedia

    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. 9-RES-JB
    11. 7577
    Prev
    Next
    INDEX
    Explanations

    names or terms containing specific syllables or sounds

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to clarity and freedom from constraints

    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
     iP
    -0.82
     Kits
    -0.78
     meg
    -0.77
     weap
    -0.76
     Helic
    -0.74
     Cu
    -0.74
     Fitz
    -0.73
     acron
    -0.72
     BI
    -0.72
     Yar
    -0.72
    POSITIVE LOGITS
    animous
    1.14
    ested
    1.12
    ired
    1.07
    irable
    1.06
    iless
    1.06
    itionally
    1.05
    unction
    1.04
    idation
    1.03
    idy
    1.02
    empt
    1.02
    Activations Density 0.222%

    No Known Activations