© 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. 8-RES-JB
    11. 7850
    Prev
    Next
    INDEX
    Explanations

    phrases related to casual conversation and social interactions

    oai_token-act-pair · gpt-3.5-turbo

    dialogues and interactions that include questions or conversational prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prisingly
    -0.83
    etheless
    -0.74
    ometimes
    -0.72
    ricanes
    -0.70
    surprisingly
    -0.70
    uitive
    -0.68
    asive
    -0.65
    ãĤ´ãĥ³
    -0.62
    mittedly
    -0.61
    eatures
    -0.61
    POSITIVE LOGITS
    '"
    1.69
    ]"
    1.47
    .")
    1.46
    "]
    1.44
    >"
    1.42
    ")
    1.38
    }"
    1.38
    ").
    1.37
    ',"
    1.37
     âĢ¦"
    1.34
    Activations Density 0.383%

    No Known Activations