© 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. 14564
    Prev
    Next
    INDEX
    Explanations

    terms related to architecture and communal spaces

    oai_token-act-pair · gpt-3.5-turbo

    terms related to preferences, communal experiences, and reclamation or salvage

    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
    otomy
    -0.85
    reon
    -0.73
    oria
    -0.73
    ento
    -0.72
    minster
    -0.71
    erion
    -0.70
    ois
    -0.69
    orius
    -0.68
    aghd
    -0.67
    onia
    -0.67
    POSITIVE LOGITS
     reclaimed
    0.72
     sprink
    0.70
    ãĥ¥
    0.70
    ization
    0.69
    iser
    0.69
    ciplinary
    0.67
     jo
    0.66
    izers
    0.66
    oller
    0.65
    glas
    0.65
    Activations Density 0.047%

    No Known Activations