© 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. 23929
    Prev
    Next
    INDEX
    Explanations

    terms related to specific methods or procedures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of methods or systems related to processes or techniques

    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
    enda
    -0.72
     stocking
    -0.66
     Childhood
    -0.63
     Chapters
    -0.62
     dreaming
    -0.62
     Oval
    -0.60
     cush
    -0.60
     harbour
    -0.60
     Cargo
    -0.60
    cot
    -0.59
    POSITIVE LOGITS
    ologies
    1.11
    ologically
    1.01
     method
    0.95
    heny
    0.93
    method
    0.90
    ologic
    0.90
    ical
    0.89
    Override
    0.87
    ically
    0.86
    idable
    0.85
    Activations Density 0.015%

    No Known Activations