Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10516
    Prev
    Next
    INDEX
    Explanations

    subscription-related prompts or actions in text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to email subscriptions

    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
     scapego
    -0.70
     dwar
    -0.64
     bil
    -0.58
    clud
    -0.57
     epit
    -0.56
    dan
    -0.55
    igi
    -0.54
    imer
    -0.54
    ial
    -0.53
     helic
    -0.52
    POSITIVE LOGITS
     Sop
    0.64
    ribly
    0.64
     WRITE
    0.62
    POSE
    0.62
    msg
    0.60
    à¼
    0.59
     Pastebin
    0.58
     Flavoring
    0.57
    ãĤ®
    0.57
    UTH
    0.57
    Activations Density 0.014%

    No Known Activations