© 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. 6-RES-JB
    6. 20438
    Prev
    Next
    INDEX
    Explanations

    mentions of technical specifications and materials used in manufacturing products

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and features related to electronics and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":[{"
    -0.86
    population
    -0.80
    Politics
    -0.79
    Blog
    -0.79
    pedia
    -0.78
    wat
    -0.77
    podcast
    -0.77
    blogs
    -0.74
     Situation
    -0.74
    "]=>
    -0.74
    POSITIVE LOGITS
     alloy
    0.99
     polymer
    0.92
     silicone
    0.92
     patented
    0.91
     adjustable
    0.91
     removable
    0.91
     molded
    0.86
     certified
    0.85
     blend
    0.85
     bonded
    0.84
    Activations Density 0.566%

    No Known Activations