© 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. 22562
    Prev
    Next
    INDEX
    Explanations

    the prefix "neo-" followed by a word stem

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of subatomic particle or phenomena related to them

    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
    DragonMagazine
    -0.89
    ãĤ·ãĥ£
    -0.88
    MODE
    -0.79
    ãĥ¼ãĥĨãĤ£
    -0.76
    姫
    -0.75
    hips
    -0.72
    AGES
    -0.71
    Ú
    -0.70
    DERR
    -0.69
    DOWN
    -0.68
    POSITIVE LOGITS
    arest
    0.93
    pher
    0.86
    verend
    0.84
    uter
    0.80
    ighth
    0.80
    thal
    0.79
    braska
    0.79
    icol
    0.79
    ccess
    0.77
    cro
    0.76
    Activations Density 0.008%

    No Known Activations