© 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. 1-RES-JB
    11. 3130
    Prev
    Next
    INDEX
    Explanations

    topics or instances of discussion

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "discussion"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.76
    sole
    -0.74
    aches
    -0.71
    otto
    -0.71
    inker
    -0.69
    ells
    -0.68
    redit
    -0.67
    uilt
    -0.67
    alties
    -0.66
    inates
    -0.66
    POSITIVE LOGITS
     discussion
    1.18
     Discussion
    1.03
     discussions
    1.00
     Topics
    0.97
     forum
    0.94
     Discuss
    0.93
     discussing
    0.90
     debates
    0.88
    atorium
    0.85
     debate
    0.83
    Activations Density 0.014%

    No Known Activations