© 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. 9-RES-JB
    11. 16461
    Prev
    Next
    INDEX
    Explanations

    phrases related to business organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of companies or organizations and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anyway
    -1.00
     scept
    -0.94
     stuff
    -0.89
     maths
    -0.89
     dod
    -0.89
    Anyway
    -0.85
     kinda
    -0.84
     rubbish
    -0.84
     messing
    -0.82
     civilisation
    -0.79
    POSITIVE LOGITS
    ®,
    1.11
    ®
    0.95
     Sponsor
    0.93
    quartered
    0.90
    âĦ¢:
    0.87
     Particip
    0.86
     utilize
    0.81
     utilizing
    0.78
    NYSE
    0.78
     utilizes
    0.77
    Activations Density 1.497%

    No Known Activations