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. 8-RES-JB
    6. 9534
    Prev
    Next
    INDEX
    Explanations

    phrases related to expectations or predictions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific excerpts or sections within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sawyer
    -0.71
     GOODMAN
    -0.71
    OOD
    -0.66
    LIN
    -0.65
    enegger
    -0.64
    NING
    -0.63
     Rough
    -0.61
    WARE
    -0.61
     scaff
    -0.59
    die
    -0.59
    POSITIVE LOGITS
    haust
    1.39
    cerpt
    1.27
    terior
    1.26
    cessive
    1.25
    pert
    1.24
    ternally
    1.23
    ceptions
    1.22
    clamation
    1.20
    changes
    1.18
    pect
    1.18
    Activations Density 0.031%

    No Known Activations