© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 21882
    Prev
    Next
    INDEX
    Explanations

    documents or references to various documents

    oai_token-act-pair · gpt-3.5-turbo

    references to official documents and files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -1.00
    stad
    -0.74
    ntil
    -0.73
    âĶģ
    -0.73
    nen
    -0.71
    culosis
    -0.70
    ategory
    -0.69
    Õ
    -0.68
    cers
    -0.67
    irth
    -0.67
    POSITIVE LOGITS
     documents
    0.99
     pertaining
    0.97
     detailing
    0.93
    hig
    0.89
     relating
    0.88
     stored
    0.86
     trove
    0.86
     retrieved
    0.84
     files
    0.83
     obtained
    0.83
    Activations Density 0.048%

    No Known Activations