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. 3520
    Prev
    Next
    INDEX
    Explanations

    mentions of events or incidents involving death or serious injury

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events that occur after a specified incident

    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
    isa
    -0.82
    aez
    -0.79
    女
    -0.74
    available
    -0.74
    ertain
    -0.73
    OE
    -0.73
    ãĥ¼
    -0.72
    Else
    -0.72
    CHR
    -0.72
    ophobia
    -0.72
    POSITIVE LOGITS
     ingest
    0.99
     consuming
    0.92
     sustaining
    0.92
     receiving
    0.88
     undergoing
    0.88
     encountering
    0.88
     completing
    0.87
     witnessing
    0.87
     collapsing
    0.87
     exchanging
    0.86
    Activations Density 0.109%

    No Known Activations