© 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. 1-RES-JB
    11. 10322
    Prev
    Next
    INDEX
    Explanations

    references to the location "Aspen Institute"

    oai_token-act-pair · gpt-3.5-turbo

    words related to the "pen" or pen-related themes, indicating a focus on writing or creative expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirds
    -0.69
     Greeks
    -0.67
     BaseType
    -0.65
     Hep
    -0.65
     Normandy
    -0.64
     HIP
    -0.62
     GEAR
    -0.62
     Blueprint
    -0.62
    OST
    -0.61
     CNS
    -0.59
    POSITIVE LOGITS
    insula
    1.27
    pen
    1.27
    cil
    1.20
    alties
    1.15
    itent
    1.15
    ultimate
    1.07
    ning
    0.99
    Pen
    0.96
    elope
    0.93
    issance
    0.92
    Activations Density 0.005%

    No Known Activations