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. 3-RES-JB
    6. 19204
    Prev
    Next
    INDEX
    Explanations

    references to specific streaming services like Hulu and devices compatible with them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of streaming services, particularly Hulu

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cycl
    -0.85
    rian
    -0.69
    ggies
    -0.65
    race
    -0.64
    eds
    -0.64
    urb
    -0.63
    td
    -0.62
    akable
    -0.62
    rians
    -0.61
    ourke
    -0.61
    POSITIVE LOGITS
     Hulu
    1.02
     Roku
    0.82
     Mub
    0.73
    awei
    0.73
     Streaming
    0.72
     Analytics
    0.71
     Plus
    0.69
     Glacier
    0.69
    conn
    0.68
     Sparrow
    0.67
    Activations Density 0.007%

    No Known Activations