© 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. 6-RES-JB
    11. 13541
    Prev
    Next
    INDEX
    Explanations

    specific statements, opinions, or arguments made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    assertions about societal responsibilities and cultural critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.55
     Pwr
    -0.51
    Attempts
    -0.51
    Spot
    -0.49
    Details
    -0.49
     Laboratory
    -0.48
     Magicka
    -0.48
     NAD
    -0.48
    odder
    -0.47
     sqor
    -0.47
    POSITIVE LOGITS
     "'
    0.65
     homosexuals
    0.64
     persecuted
    0.63
     undermin
    0.63
     immoral
    0.62
     somehow
    0.61
     rapists
    0.60
     "âĢ¦
    0.60
     oppress
    0.57
     "#
    0.57
    Activations Density 1.337%

    No Known Activations