© 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. 7-RES-JB
    11. 17080
    Prev
    Next
    INDEX
    Explanations

    education-related entities, such as colleges, schools, and campuses

    oai_token-act-pair · gpt-3.5-turbo

    references to educational institutions, locations, and organizations

    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
     Guru
    -0.57
     largeDownload
    -0.57
     annexation
    -0.55
    rontal
    -0.55
    NK
    -0.54
     calm
    -0.54
     Humane
    -0.54
     Wa
    -0.53
     Maw
    -0.52
     Gun
    -0.52
    POSITIVE LOGITS
     imaginable
    1.06
     alike
    0.92
     vying
    0.92
     besides
    0.85
     irrespective
    0.84
     including
    0.84
    hips
    0.83
     worldwide
    0.82
     nationwide
    0.81
     simultaneously
    0.81
    Activations Density 0.401%

    No Known Activations