© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 22500
    Prev
    Next
    INDEX
    Explanations

    mentions of the technology company AMD

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company AMD and its products or technologies

    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
    glers
    -0.99
    vous
    -0.79
    arters
    -0.74
    pees
    -0.74
    icho
    -0.74
    apest
    -0.71
    bucks
    -0.71
     Doe
    -0.70
    arter
    -0.70
    pee
    -0.69
    POSITIVE LOGITS
    GPU
    1.21
     Ryzen
    1.05
     Radeon
    1.01
    gpu
    0.96
    AMD
    0.80
    adeon
    0.78
    erity
    0.78
     processors
    0.76
    BILITIES
    0.76
     chips
    0.74
    Activations Density 0.030%

    No Known Activations