© 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. 23806
    Prev
    Next
    INDEX
    Explanations

    references to plans, resources, and investments

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of the word "the" in various contexts

    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
     whilst
    -0.78
    ghazi
    -0.75
    assed
    -0.75
    arse
    -0.73
    strate
    -0.73
    !!!!
    -0.72
    ogyn
    -0.71
    thood
    -0.71
    Scotland
    -0.71
    !!!
    -0.70
    POSITIVE LOGITS
    oret
    1.34
     feds
    1.11
     biggest
    1.07
     downside
    1.04
     latest
    0.98
     easiest
    0.97
     newest
    0.97
    ories
    0.96
     idea
    0.94
     simplest
    0.94
    Activations Density 0.711%

    No Known Activations