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. 9-RES-JB
    6. 785
    Prev
    Next
    INDEX
    Explanations

    mentions of illicit romantic relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to situations characterized by having or experiencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arning
    -0.75
    ensing
    -0.71
    NESS
    -0.70
    adj
    -0.65
     Posts
    -0.64
    quartered
    -0.64
    available
    -0.64
    yond
    -0.64
    aware
    -0.63
    UC
    -0.63
    POSITIVE LOGITS
     meltdown
    0.98
     chance
    0.95
    iphany
    0.93
     intercourse
    0.89
     conversation
    0.88
     affair
    0.86
     conversations
    0.85
     dealings
    0.85
     blast
    0.84
     luck
    0.84
    Activations Density 0.212%

    No Known Activations