© 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. 16104
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical interaction or control, like "finger on the trigger" or "hands on the wheel"

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to control and attention

    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
    ipel
    -0.75
    named
    -0.74
    ousy
    -0.70
    IUM
    -0.69
    illac
    -0.68
    isal
    -0.67
    ischer
    -0.66
    isure
    -0.65
     Associ
    -0.64
    umbai
    -0.63
    POSITIVE LOGITS
     hers
    0.86
    stretched
    0.73
     shoulder
    0.73
     theirs
    0.70
     microphone
    0.69
     necks
    0.68
     steering
    0.68
     shoulders
    0.68
     scissors
    0.65
     keyboard
    0.65
    Activations Density 0.140%

    No Known Activations