Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 10072
    Prev
    Next
    INDEX
    Explanations

    topics or subjects of discussion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "topic" and related discussions

    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
    ignt
    -0.79
    urses
    -0.76
     satell
    -0.72
    onies
    -0.69
    otted
    -0.68
    alties
    -0.68
    hovah
    -0.67
    aquin
    -0.66
    artney
    -0.66
    leeve
    -0.66
    POSITIVE LOGITS
    topic
    0.99
     topic
    0.95
    Topics
    0.94
    Topic
    0.91
     topics
    0.84
     Topics
    0.83
    Problem
    0.82
    naire
    0.80
    TextColor
    0.79
    menu
    0.77
    Activations Density 0.010%

    No Known Activations