© 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. 7273
    Prev
    Next
    INDEX
    Explanations

    words related to experimenting, trying out, or playing around with different things or ideas

    oai_token-act-pair · gpt-3.5-turbo

    references to experimentation and trying new ideas

    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
    CVE
    -0.75
    ict
    -0.74
    DragonMagazine
    -0.74
    avorable
    -0.70
    DEF
    -0.70
     [+
    -0.68
    vation
    -0.66
     Defendants
    -0.65
     Persons
    -0.65
    gio
    -0.65
    POSITIVE LOGITS
     ways
    0.81
     experimenting
    0.80
     strategies
    0.80
     tweaking
    0.79
    nels
    0.76
     layouts
    0.76
     tink
    0.76
     tactics
    0.75
     wildly
    0.74
     ideas
    0.74
    Activations Density 0.210%

    No Known Activations