© 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. 17848
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names and related references in a narrative context

    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
     Wim
    -0.66
    soType
    -0.63
     Quadro
    -0.60
    Apply
    -0.60
     Judd
    -0.58
     EMS
    -0.58
    Compare
    -0.57
     Capcom
    -0.56
     Apply
    -0.56
    taboola
    -0.55
    POSITIVE LOGITS
     disappeared
    0.72
     vanished
    0.68
     shortage
    0.67
     indeed
    0.64
    undrum
    0.62
     saga
    0.61
     vanishing
    0.61
     harmed
    0.61
     vanish
    0.60
    iasis
    0.60
    Activations Density 1.057%

    No Known Activations