© 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. 639
    Prev
    Next
    INDEX
    Explanations

    mentions of high values or degrees in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to high rates or levels of various phenomena

    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
    Rect
    -0.82
    Sham
    -0.80
    herer
    -0.76
    uphem
    -0.74
    glass
    -0.71
    è
    -0.70
    pty
    -0.70
    them
    -0.69
    vier
    -0.68
    fits
    -0.66
    POSITIVE LOGITS
     incidence
    1.25
     prices
    1.23
     prevalence
    1.23
     rates
    1.22
     amounts
    1.22
     levels
    1.17
     temperatures
    1.16
     percentage
    1.14
     concentrations
    1.14
     susceptibility
    1.13
    Activations Density 0.126%

    No Known Activations