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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6799
    Prev
    Next
    INDEX
    Explanations

    relations between two concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to gender differences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pletion
    -0.79
    ogle
    -0.78
    oho
    -0.73
    phies
    -0.72
    anson
    -0.72
    city
    -0.72
     Shutterstock
    -0.71
    akery
    -0.71
    ervation
    -0.71
    ocalypse
    -0.67
    POSITIVE LOGITS
     mutually
    1.56
     differing
    1.24
     halves
    1.22
     alike
    1.22
     respectively
    1.20
     jointly
    1.18
     insepar
    1.15
     together
    1.12
     respective
    1.11
     separated
    1.09
    Activations Density 0.882%

    No Known Activations