© 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. 2-RES-JB
    11. 23905
    Prev
    Next
    INDEX
    Explanations

    references to leather or leather-related items

    oai_token-act-pair · gpt-3.5-turbo

    references to leather and leather-related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MIT
    -0.76
     Fas
    -0.74
    éĹĺ
    -0.71
    owers
    -0.71
    NPR
    -0.70
    itia
    -0.69
     Miranda
    -0.69
    PsyNetMessage
    -0.69
     Nurs
    -0.69
     CPS
    -0.67
    POSITIVE LOGITS
     leather
    1.19
     straps
    1.06
    worm
    0.95
    worms
    0.93
     jackets
    0.93
     strap
    0.90
    bag
    0.88
    clad
    0.86
    skin
    0.85
     bags
    0.85
    Activations Density 0.008%

    No Known Activations