© 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. 8-RES-JB
    11. 18571
    Prev
    Next
    INDEX
    Explanations

    phrases related to commentary and analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss societal issues and perceptions

    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
    bol
    -0.75
    ãĤ´ãĥ³
    -0.70
    æĪ¦
    -0.65
    ãĥĭ
    -0.65
     Grounds
    -0.62
    ãĥ¤
    -0.61
    packed
    -0.60
     awaits
    -0.59
    éĹĺ
    -0.58
    fitted
    -0.57
    POSITIVE LOGITS
     people
    0.93
     nowadays
    0.93
     society
    0.91
     societal
    0.91
    People
    0.90
     stagnant
    0.88
     everybody
    0.86
     societies
    0.86
     millennials
    0.86
    Everybody
    0.83
    Activations Density 0.859%

    No Known Activations