© 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. 10-RES-JB
    11. 2964
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific organizations or institutional names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations and entities related to assessments and social services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     burner
    -0.82
     captcha
    -0.77
     impulse
    -0.76
    agame
    -0.76
     heel
    -0.75
     microbiome
    -0.75
     streak
    -0.74
     ellipt
    -0.73
     flask
    -0.73
     experiment
    -0.73
    POSITIVE LOGITS
     Solutions
    1.49
     Services
    1.44
     Partners
    1.37
     Advis
    1.31
     Month
    1.28
     Associates
    1.28
     Ltd
    1.26
     Ventures
    1.22
     Inc
    1.20
     Association
    1.19
    Activations Density 0.323%

    No Known Activations