© 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. 7-RES-JB
    11. 8829
    Prev
    Next
    INDEX
    Explanations

    connections or interactions involving the action of bolting or fastening in a mechanical context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mechanical components and assembly processes

    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
     Carbuncle
    -0.83
    ¥µ
    -0.83
     Atmosp
    -0.82
    ceans
    -0.80
    estial
    -0.77
    SPONSORED
    -0.73
    天
    -0.72
    issance
    -0.72
    veyard
    -0.71
     Sprite
    -0.69
    POSITIVE LOGITS
     clamp
    1.11
     weld
    1.10
     molded
    1.06
     securely
    1.02
     diameter
    1.00
     attaching
    1.00
     screws
    0.93
    driver
    0.93
     connector
    0.91
     holes
    0.91
    Activations Density 0.187%

    No Known Activations