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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 15956
    Prev
    Next
    INDEX
    Explanations

    references to professors and their related activities or attributions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific professors or academic titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENTS
    -0.79
    boat
    -0.76
     leash
    -0.75
    RANT
    -0.72
     cruc
    -0.69
    boats
    -0.67
    doors
    -0.67
    witz
    -0.67
     ashore
    -0.66
    MENT
    -0.65
    POSITIVE LOGITS
    essors
    1.58
    iciency
    1.31
    iles
    1.27
    essor
    1.24
    icient
    1.16
    ession
    1.12
    ound
    1.04
    essed
    0.98
    ository
    0.98
    essions
    0.98
    Activations Density 0.014%

    No Known Activations