© 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. 9-RES-JB
    11. 21538
    Prev
    Next
    INDEX
    Explanations

    words related to different types of ground materials, especially mud and rock

    oai_token-act-pair · gpt-3.5-turbo

    references to mud and rock-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fn
    -0.75
    FontSize
    -0.71
     RPM
    -0.70
    ITED
    -0.69
     attendance
    -0.68
     Alic
    -0.67
     antioxid
    -0.66
    CTV
    -0.66
    ONSORED
    -0.64
     Monetary
    -0.64
    POSITIVE LOGITS
    fields
    1.15
     formations
    1.10
     piles
    1.08
    flows
    0.98
    bags
    0.97
     tunnels
    0.95
     mound
    0.92
     trails
    0.91
     quar
    0.91
     surfaces
    0.89
    Activations Density 0.140%

    No Known Activations