© 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. 7-RES-JB
    11. 23781
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to organizations and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toggle
    -0.84
    orce
    -0.78
     nasty
    -0.77
    maybe
    -0.77
    Enlarge
    -0.76
     piss
    -0.71
     pee
    -0.71
    stuff
    -0.71
     sucker
    -0.70
     worse
    -0.70
    POSITIVE LOGITS
     accredited
    0.93
     collabor
    0.93
     strives
    0.89
     collaborative
    0.86
     Cosponsors
    0.83
     DOE
    0.82
     collaborating
    0.81
     initiatives
    0.81
     innovative
    0.80
     fost
    0.80
    Activations Density 1.025%

    No Known Activations