© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9438
    Prev
    Next
    INDEX
    Explanations

    web URLs and links

    oai_token-act-pair · gpt-3.5-turbo

    URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Morse
    -0.74
     unsus
    -0.73
     sided
    -0.71
     Nig
    -0.69
    mable
    -0.65
     Bung
    -0.65
     Takeru
    -0.65
    senal
    -0.65
     Tay
    -0.64
     lab
    -0.63
    POSITIVE LOGITS
    www
    1.60
    natureconservancy
    1.51
    ://
    1.34
    youtu
    1.14
    goo
    1.06
    past
    1.03
    doi
    1.02
    archive
    0.99
    twitter
    0.98
    bit
    0.98
    Activations Density 0.017%

    No Known Activations