© 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. 8-RES-JB
    11. 1031
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of receding or retreating

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the word "rec."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENT
    -0.76
    MENTS
    -0.75
    nuts
    -0.69
    NESS
    -0.66
     GOODMAN
    -0.66
     Nest
    -0.66
     heaven
    -0.65
    loo
    -0.65
     Masters
    -0.64
    buster
    -0.63
    POSITIVE LOGITS
    ategor
    1.19
    ourses
    1.18
    ievers
    1.14
    ieving
    1.11
    usal
    1.06
    iever
    1.06
    oding
    1.05
    urrence
    1.02
    ursion
    1.02
    aution
    1.01
    Activations Density 0.011%

    No Known Activations