© 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. 4-RES-JB
    11. 20862
    Prev
    Next
    INDEX
    Explanations

    Proper names and affiliations of entities, potentially related to a specific context

    oai_token-act-pair · gpt-3.5-turbo

    references to the Muppets or related characters

    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
    GW
    -0.72
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
     willful
    -0.72
    76561
    -0.69
    å°Ĩ
    -0.68
     logger
    -0.67
     corrosion
    -0.67
     dissolution
    -0.65
    binding
    -0.64
     frustration
    -0.63
    POSITIVE LOGITS
    ortun
    1.16
    olicy
    1.12
    sburgh
    1.11
    enhagen
    1.09
    enthal
    1.03
    etry
    1.02
    esy
    0.99
    onent
    0.99
    ete
    0.98
    odcast
    0.95
    Activations Density 0.007%

    No Known Activations