© 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. 9186
    Prev
    Next
    INDEX
    Explanations

    references to in-depth investigation or thorough analysis

    oai_token-act-pair · gpt-3.5-turbo

    the word "extensive."

    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
     Alive
    -0.72
    pal
    -0.69
    Frames
    -0.69
    gged
    -0.67
    alias
    -0.67
    nery
    -0.67
    Safe
    -0.66
    fighter
    -0.66
    pos
    -0.66
    Earth
    -0.65
    POSITIVE LOGITS
     amounts
    0.96
     extensive
    0.82
     portions
    0.80
     thorough
    0.78
     quantities
    0.77
    mble
    0.74
     tracts
    0.73
     disadvantages
    0.72
     stretches
    0.72
     expansions
    0.70
    Activations Density 0.008%

    No Known Activations