© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22082
    Prev
    Next
    INDEX
    Explanations

    words related to rigidity, stiffness, and inflexibility

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rigidity and elasticity in materials

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

    No Comments

    Negative Logits
    swick
    -0.85
    orks
    -0.81
    arnaev
    -0.79
    plain
    -0.78
    ulhu
    -0.77
    urai
    -0.77
     Pension
    -0.75
    elf
    -0.74
    umbn
    -0.73
    ovember
    -0.70
    POSITIVE LOGITS
     friction
    1.01
     recoil
    1.00
     adhesive
    0.89
     rubber
    0.87
     latex
    0.83
     fracturing
    0.82
     piston
    0.81
     actu
    0.81
     mortar
    0.80
     bonded
    0.79
    Activations Density 0.036%

    No Known Activations