© 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
    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. 6161
    Prev
    Next
    INDEX
    Explanations

    keywords related to software and technology

    oai_token-act-pair · gpt-3.5-turbo

    content related to technology and digital applications

    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
    Again
    -0.72
    again
    -0.70
    anooga
    -0.68
     meanwhile
    -0.66
    Same
    -0.61
    also
    -0.60
    ````
    -0.59
    displayText
    -0.59
    still
    -0.58
    step
    -0.58
    POSITIVE LOGITS
     Ethereum
    0.58
     Kickstarter
    0.56
     FIFA
    0.54
     Bitcoins
    0.54
     TYPE
    0.54
     Kappa
    0.53
     Sega
    0.53
     Protoss
    0.52
     Minecraft
    0.52
     SCP
    0.51
    Activations Density 1.477%

    No Known Activations