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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 5596
    Prev
    Next
    INDEX
    Explanations

    dialogue lines in quotations

    oai_token-act-pair · gpt-3.5-turbo

    dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pole
    -0.89
     undersc
    -0.77
     crafts
    -0.77
     litter
    -0.76
     characterized
    -0.76
     replacement
    -0.74
     revers
    -0.74
     consumer
    -0.74
     frontline
    -0.74
     targeted
    -0.73
    POSITIVE LOGITS
    Hey
    1.53
    Oh
    1.47
    Yeah
    1.40
    Fuck
    1.40
    Sorry
    1.36
    Hmm
    1.36
    Yes
    1.36
    What
    1.34
    Why
    1.34
    Huh
    1.32
    Activations Density 0.115%

    No Known Activations