© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12716
    Prev
    Next
    INDEX
    Explanations

    words related to motives and profitability

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to profit, motives, and outcomes of choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )",
    -0.58
    razil
    -0.52
    ©¶æ
    -0.49
    ographs
    -0.49
    )"
    -0.46
    yss
    -0.45
     Satanic
    -0.44
    ]"
    -0.44
    odan
    -0.44
    Ò
    -0.44
    POSITIVE LOGITS
     nonetheless
    1.02
    .
    0.94
    .*
    0.93
    *.
    0.92
     anytime
    0.85
     anyway
    0.85
    .#
    0.84
    .(
    0.84
     anyways
    0.84
    .</
    0.83
    Activations Density 0.962%

    No Known Activations