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. 7-RES-JB
    6. 18510
    Prev
    Next
    INDEX
    Explanations

    phrases where something is designed or created with a specific purpose or device in mind

    oai_token-act-pair · gpt-3.5-turbo

    references to considerations or context that influences decision-making or design

    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
    EStreamFrame
    -0.74
    iott
    -0.62
    imer
    -0.61
    Reviewed
    -0.61
     coefficient
    -0.59
     Rumble
    -0.59
    quer
    -0.59
    dayName
    -0.58
    abs
    -0.58
    VD
    -0.57
    POSITIVE LOGITS
    omsday
    0.86
    fulness
    0.71
    lessly
    0.70
    oldown
    0.66
     Kamp
    0.65
     holistic
    0.64
     hurry
    0.61
    swer
    0.61
    ovie
    0.61
    essage
    0.61
    Activations Density 0.017%

    No Known Activations