© 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. 6-RES-JB
    11. 13627
    Prev
    Next
    INDEX
    Explanations

    references to names and terms related to astrophysics and personal names starting with "Matth"

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to astrophysics and its key figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SER
    -0.74
     Machina
    -0.70
    DEN
    -0.69
    venient
    -0.67
    fax
    -0.67
    nexus
    -0.67
    sequence
    -0.67
    esis
    -0.65
    PRESS
    -0.65
    lia
    -0.65
    POSITIVE LOGITS
    ots
    1.03
    ock
    0.89
    azer
    0.89
    ift
    0.88
    atform
    0.88
    iolet
    0.87
    otive
    0.87
    urst
    0.87
    unks
    0.86
    izoph
    0.86
    Activations Density 0.073%

    No Known Activations