© 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. 8-RES-JB
    11. 6034
    Prev
    Next
    INDEX
    Explanations

    proper nouns, likely related to brands, products, or titles

    oai_token-act-pair · gpt-3.5-turbo

    capital letters or references to specific characters or elements

    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
     Journals
    -0.63
     ageing
    -0.63
     reprodu
    -0.62
     Browse
    -0.62
     aging
    -0.61
     butterflies
    -0.61
     uncertain
    -0.60
     graphs
    -0.59
    lining
    -0.59
     ital
    -0.59
    POSITIVE LOGITS
    OT
    1.01
    OD
    0.99
    BS
    0.96
    OPA
    0.96
    JD
    0.94
    BC
    0.93
    ISS
    0.92
    XY
    0.92
    ISC
    0.91
    EO
    0.90
    Activations Density 0.131%

    No Known Activations