© 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. 2-RES-JB
    6. 3163
    Prev
    Next
    INDEX
    Explanations

    terms related to interactive content or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of interactive features or components

    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
    ioxide
    -0.84
    aws
    -0.77
    gans
    -0.76
    arest
    -0.76
    hovah
    -0.74
    ady
    -0.74
    aimon
    -0.74
    yards
    -0.72
    iffs
    -0.72
    ayer
    -0.71
    POSITIVE LOGITS
     interactive
    1.03
     slideshow
    0.83
     multimedia
    0.81
     theatre
    0.79
     exhibition
    0.72
     showc
    0.72
     kios
    0.71
     screens
    0.70
     session
    0.69
     touchscreen
    0.68
    Activations Density 0.016%

    No Known Activations