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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 1309
    Prev
    Next
    INDEX
    Explanations

    price-related information and deals

    oai_token-act-pair · gpt-3.5-turbo

    pricing information and special offers for products

    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
     epidem
    -0.92
     folklore
    -0.78
     statistical
    -0.76
     causal
    -0.74
     coordin
    -0.74
     deposition
    -0.73
    nesota
    -0.73
     teamwork
    -0.73
     linguistic
    -0.72
     systemic
    -0.72
    POSITIVE LOGITS
    /$
    1.14
     priced
    1.03
    AU
    1.01
     pric
    1.00
     £
    1.00
    price
    0.99
    £
    0.98
     cheapest
    0.98
     Discount
    0.97
     âĤ¬
    0.97
    Activations Density 0.399%

    No Known Activations