© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    references to 'higher' concepts or levels

    oai_token-act-pair · gpt-3.5-turbo

    references to "higher" in various contexts related to advancement or improvement

    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
    pty
    -0.77
    mir
    -0.67
    icia
    -0.67
    ãĤ£
    -0.64
    oris
    -0.61
    Deal
    -0.61
    Bio
    -0.61
    icons
    -0.61
     Outbreak
    -0.60
    oire
    -0.60
    POSITIVE LOGITS
     than
    1.06
    than
    0.97
     levels
    0.96
     tiers
    0.95
     priced
    0.93
     earners
    0.91
     grades
    0.87
     pitched
    0.87
     ceilings
    0.86
    iating
    0.82
    Activations Density 0.032%

    No Known Activations