© 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. 9-RES-JB
    6. 8740
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical or scientific concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific concepts and terms related to health and immunity

    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
     Hort
    -0.66
     Tsukuyomi
    -0.65
    ··
    -0.64
    thora
    -0.64
     Takeru
    -0.63
    taboola
    -0.61
    hod
    -0.61
    sson
    -0.60
     Rapp
    -0.60
    ibur
    -0.58
    POSITIVE LOGITS
     shorthand
    1.13
     abbre
    0.93
    meaning
    0.91
     acronym
    0.90
     whereby
    0.89
     loosely
    0.84
     grouping
    0.83
     refers
    0.81
     essentially
    0.80
     basically
    0.80
    Activations Density 0.540%

    No Known Activations