© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5875
    Prev
    Next
    INDEX
    Explanations

    actions and interactions involving people

    oai_token-act-pair · gpt-3.5-turbo

    expressions and terminology related to consent and interpersonal relationships

    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
     sqor
    -0.73
    ivery
    -0.68
    Magikarp
    -0.68
    flex
    -0.67
    iasm
    -0.66
     Jr
    -0.65
    Jr
    -0.64
     respectively
    -0.63
    æ©Ł
    -0.63
    )}
    -0.61
    POSITIVE LOGITS
     herself
    2.78
     her
    1.77
     husband
    1.40
     she
    1.27
     hers
    1.25
     boyfriend
    1.21
     She
    1.16
     HER
    1.15
    Her
    1.13
     SHE
    1.10
    Activations Density 0.773%

    No Known Activations