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. 8-RES-JB
    6. 23296
    Prev
    Next
    INDEX
    Explanations

    references to a particular television show

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific television shows

    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
    quez
    -0.69
     steel
    -0.66
    ntil
    -0.65
     solitary
    -0.65
     Lucia
    -0.62
    illard
    -0.62
     scarce
    -0.62
     Aval
    -0.62
     granite
    -0.62
     saline
    -0.61
    POSITIVE LOGITS
    runners
    1.60
    biz
    1.56
    runner
    1.55
    manship
    1.14
    mable
    1.11
    room
    1.04
    case
    0.99
    girls
    0.97
    downs
    0.95
    rooms
    0.95
    Activations Density 0.043%

    No Known Activations