© 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. 7097
    Prev
    Next
    INDEX
    Explanations

    items related to official documentation or forms

    oai_token-act-pair · gpt-3.5-turbo

    references to documents or entities associated with formal procedures and lists

    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
    qi
    -0.73
    jee
    -0.73
    agy
    -0.72
    ledge
    -0.68
    flows
    -0.68
    bil
    -0.67
    Cho
    -0.67
    hap
    -0.66
    iev
    -0.65
    ibl
    -0.64
    POSITIVE LOGITS
     sake
    1.84
     purposes
    1.58
     upcoming
    1.27
     purpose
    1.22
     foreseeable
    1.07
     remainder
    1.00
    ummies
    0.94
     duration
    0.91
     forthcoming
    0.89
     sexes
    0.89
    Activations Density 0.274%

    No Known Activations