© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    terms related to abilities and characteristics associated with physical movement and structure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to metrics, performance, and characteristics 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
    verbs
    -0.74
    zan
    -0.73
    icus
    -0.72
    alus
    -0.69
    iversal
    -0.68
    olutely
    -0.67
    ipel
    -0.66
    culosis
    -0.66
    renheit
    -0.66
    ËĪ
    -0.64
    POSITIVE LOGITS
     aspects
    0.89
     industries
    0.89
     portion
    0.87
     thereof
    0.85
     portions
    0.85
     sectors
    0.84
     aspect
    0.81
     respectively
    0.77
     phases
    0.77
     alike
    0.77
    Activations Density 0.292%

    No Known Activations