© 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 EvalsExportsinterp-engineNEWAPI 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. 1227
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific period of time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    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
    Cho
    -0.74
    gall
    -0.64
    ibr
    -0.60
    cles
    -0.60
    ãĥ³
    -0.60
    venants
    -0.60
     Edited
    -0.59
    ´
    -0.59
    Enjoy
    -0.59
    ãĥ»
    -0.59
    POSITIVE LOGITS
     sake
    1.81
     foreseeable
    1.32
     purposes
    1.29
     entirety
    1.15
     purpose
    1.12
     remainder
    1.10
     reasons
    1.06
     duration
    1.03
     entire
    1.01
     same
    0.96
    Activations Density 0.164%

    No Known Activations