© 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. 2901
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and project management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to categories and classifications

    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
     senate
    -0.79
     bitcoin
    -0.78
    izabeth
    -0.77
     hob
    -0.77
     aback
    -0.76
     cla
    -0.76
    clinton
    -0.75
     plateau
    -0.75
     slump
    -0.74
     astronomy
    -0.74
    POSITIVE LOGITS
     Disorder
    1.49
     Profession
    1.48
     Detail
    1.44
     Purpose
    1.41
     Enhancement
    1.40
     Mouth
    1.40
     Maintenance
    1.39
     Economy
    1.39
     Capacity
    1.39
     Ratio
    1.38
    Activations Density 0.505%

    No Known Activations