© 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. 9-RES-JB
    11. 3666
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing plans, strategies, and investments

    oai_token-act-pair · gpt-3.5-turbo

    references to investment and strategic growth in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Evil
    -0.78
     misfortune
    -0.76
     Die
    -0.76
     evil
    -0.76
    death
    -0.75
     lifeless
    -0.73
     Massacre
    -0.73
     dying
    -0.72
     ruined
    -0.71
     vanished
    -0.71
    POSITIVE LOGITS
     priorit
    1.23
     prioritize
    1.19
     brainstorm
    1.09
     collabor
    1.05
     experimented
    1.03
     focused
    1.03
     iter
    1.01
     consult
    1.01
     strive
    1.01
     anecd
    1.00
    Activations Density 0.649%

    No Known Activations