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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 9071
    Prev
    Next
    INDEX
    Explanations

    references to subscribing to newsletters or clubs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "our" in various contexts

    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
    stood
    -0.88
    matter
    -0.83
    bender
    -0.75
    minster
    -0.74
    nesota
    -0.74
    chains
    -0.73
     Izan
    -0.72
    yang
    -0.70
    factor
    -0.70
     mattered
    -0.69
    POSITIVE LOGITS
     own
    1.01
    selves
    0.87
     latest
    0.87
     newest
    0.84
     editorial
    0.81
     respective
    0.79
     inaugural
    0.76
     website
    0.75
     homepage
    0.75
     Newsletter
    0.75
    Activations Density 0.047%

    No Known Activations