© 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. 17308
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues and political statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to risks and societal issues

    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
    edit
    -0.74
     Edit
    -0.67
     Annotations
    -0.65
     narrator
    -0.65
     analyse
    -0.65
     disclaimer
    -0.65
     interviewer
    -0.61
    introdu
    -0.61
    catentry
    -0.59
     Interstellar
    -0.58
    POSITIVE LOGITS
     âĢ¦"
    1.01
     ..."
    0.99
     barbaric
    0.89
     injust
    0.86
     tyranny
    0.85
    âĢ¦"
    0.85
    sic
    0.84
     oppressed
    0.83
     taxpayer
    0.82
     innocent
    0.81
    Activations Density 1.109%

    No Known Activations