© 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. 4-RES-JB
    6. 11148
    Prev
    Next
    INDEX
    Explanations

    specific mentions or instances of revisions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to revisions or changes in policies, systems, or laws

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

    No Comments

    Negative Logits
     Clancy
    -0.72
     Tribe
    -0.70
     Premiership
    -0.63
    eu
    -0.63
    ammad
    -0.63
    zzi
    -0.63
    hesda
    -0.62
    poon
    -0.62
    orld
    -0.62
    zer
    -0.60
    POSITIVE LOGITS
    ist
    1.07
     revision
    1.04
    ism
    0.94
     guiActiveUn
    0.94
    ists
    0.89
    ary
    0.84
    ition
    0.82
    itized
    0.81
    arily
    0.77
    isms
    0.76
    Activations Density 0.027%

    No Known Activations