© 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. 0-RES-JB
    11. 13381
    Prev
    Next
    INDEX
    Explanations

    organizations or groups related to educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "students"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capabilities
    -0.72
     alpha
    -0.70
     mitigation
    -0.70
     numbers
    -0.68
     ear
    -0.67
     traps
    -0.66
     defense
    -0.66
     angel
    -0.66
     breathing
    -0.66
     eye
    -0.65
    POSITIVE LOGITS
     Students
    3.49
    Students
    2.64
     Student
    2.39
    Student
    2.16
     Teachers
    1.84
     Faculty
    1.77
    student
    1.66
     Parents
    1.60
     Schools
    1.49
     Campus
    1.46
    Activations Density 0.032%

    No Known Activations