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

    Neuronpedia

    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. 1105
    Prev
    Next
    INDEX
    Explanations

    references to decisions, actions, or behaviors of a university and its affiliated groups

    oai_token-act-pair · gpt-3.5-turbo

    references to university decisions and policies

    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
     desper
    -0.76
     Pwr
    -0.75
    yip
    -0.74
     fisherman
    -0.74
     GoPro
    -0.73
    rov
    -0.72
    zbollah
    -0.72
    ustom
    -0.72
     petrol
    -0.71
    oil
    -0.71
    POSITIVE LOGITS
     campus
    2.21
     faculty
    2.11
     Faculty
    1.97
     Campus
    1.93
     campuses
    1.93
     student
    1.90
    campus
    1.90
     students
    1.89
     Student
    1.88
    Students
    1.88
    Activations Density 0.942%

    No Known Activations