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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7890
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Amazon"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Amazon company and its services

    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
     Rasm
    -0.72
    boarding
    -0.70
     Schne
    -0.69
    bil
    -0.66
     quo
    -0.65
    nered
    -0.65
    otent
    -0.65
     politic
    -0.64
    etting
    -0.64
    ROR
    -0.64
    POSITIVE LOGITS
     Kindle
    0.92
    Fresh
    0.89
     Prime
    0.86
     Echo
    0.85
     Studios
    0.83
    Prime
    0.80
     Alexa
    0.80
     Mechanical
    0.79
    ian
    0.76
     Instant
    0.75
    Activations Density 0.040%

    No Known Activations