© 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. 2-RES-JB
    11. 4415
    Prev
    Next
    INDEX
    Explanations

    phrases or text related to discussions or debates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "discussion" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensions
    -0.71
    peria
    -0.70
    inals
    -0.70
    otted
    -0.69
    ressed
    -0.68
    otto
    -0.67
    ussy
    -0.66
    uilt
    -0.66
    inker
    -0.66
    aches
    -0.66
    POSITIVE LOGITS
     discussion
    1.03
     forum
    0.98
     discussions
    0.94
     forums
    0.90
     Discuss
    0.87
     discussing
    0.87
     Discussion
    0.84
    atorium
    0.79
     discuss
    0.78
     debates
    0.78
    Activations Density 0.018%

    No Known Activations