© 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. 8-RES-JB
    11. 6351
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences or actions following a condition being met

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that indicate ongoing conditions or actions

    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
    watching
    -0.65
    vasive
    -0.64
    hered
    -0.64
    spir
    -0.63
    DX
    -0.63
    microsoft
    -0.62
    got
    -0.62
     Yourself
    -0.61
    ãĤ´ãĥ³
    -0.58
    pires
    -0.58
    POSITIVE LOGITS
     hence
    1.16
     someday
    1.14
     thereby
    1.13
     consequently
    1.10
     eventually
    1.04
     possibly
    1.03
     reap
    0.99
     terminate
    0.99
     hopefully
    0.98
     preferably
    0.98
    Activations Density 0.392%

    No Known Activations