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. 4656
    Prev
    Next
    INDEX
    Explanations

    names of people, likely from conversations or dialogue

    oai_token-act-pair · gpt-3.5-turbo

    references to names or organizations, particularly in a dialogue context

    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
     respectively
    -0.69
    BuyableInstoreAndOnline
    -0.65
     downstream
    -0.65
    gradient
    -0.62
    .","
    -0.61
     Skydragon
    -0.60
    chery
    -0.59
     ),
    -0.59
     consolidation
    -0.58
     dumping
    -0.58
    POSITIVE LOGITS
     laughs
    0.97
    %:
    0.91
    maxwell
    0.87
    ITNESS
    0.79
    Interview
    0.79
    laughs
    0.79
    :
    0.78
    laugh
    0.78
    Answer
    0.76
     laughed
    0.75
    Activations Density 0.151%

    No Known Activations