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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 11318
    Prev
    Next
    INDEX
    Explanations

    mentions of thickness and spacing in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical dimensions and properties of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTA
    -0.83
    JECT
    -0.78
     Zucker
    -0.70
    endants
    -0.69
     Angola
    -0.66
    itual
    -0.66
    Dub
    -0.65
     Central
    -0.65
    ODE
    -0.64
    administ
    -0.63
    POSITIVE LOGITS
     thickness
    1.29
    ngth
    0.86
     stiffness
    0.86
    terness
    0.85
     spacing
    0.83
     insulation
    0.82
     Seym
    0.82
     conversions
    0.80
     angle
    0.79
     slic
    0.78
    Activations Density 0.018%

    No Known Activations