© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17163
    Prev
    Next
    INDEX
    Explanations

    profession-related information about individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating occupations and roles

    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
    SPONSORED
    -0.86
    ctions
    -0.71
     sooner
    -0.70
     uncovered
    -0.69
     victorious
    -0.68
     warmed
    -0.66
    itized
    -0.66
    vation
    -0.65
     unveiled
    -0.64
     unforeseen
    -0.64
    POSITIVE LOGITS
    byss
    0.73
     mosqu
    0.72
    é¾
    0.68
     nearby
    0.66
     northeast
    0.63
     Piercing
    0.62
     condo
    0.62
     southeast
    0.61
     pestic
    0.61
     Torrent
    0.60
    Activations Density 0.304%

    No Known Activations