© 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. 20071
    Prev
    Next
    INDEX
    Explanations

    phrases related to long-term associations or tenure

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term relationships or associations

    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
    ageddon
    -0.88
    illions
    -0.84
    urgy
    -0.79
    ospace
    -0.78
    atures
    -0.77
    anguage
    -0.77
    aughtered
    -0.73
    daq
    -0.73
    amera
    -0.71
    abad
    -0.71
    POSITIVE LOGITS
     collaborator
    1.04
     associate
    0.95
     resident
    0.94
     longtime
    0.91
     ally
    0.89
     friend
    0.88
     acquaintance
    0.88
     nem
    0.86
     fascination
    0.86
     proponent
    0.86
    Activations Density 0.056%

    No Known Activations