© 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. 6-RES-JB
    11. 11653
    Prev
    Next
    INDEX
    Explanations

    lines ending with unusual characters (such as Ċ followed by a number)

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to news and reporting structures

    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
     Brandon
    -0.65
     Double
    -0.63
     Cho
    -0.62
     Deity
    -0.61
     Wrong
    -0.61
     Bowman
    -0.60
     Reincarnated
    -0.59
     Vaughn
    -0.59
     Badge
    -0.58
     rave
    -0.58
    POSITIVE LOGITS
    ccording
    0.88
    ERROR
    0.75
    WAR
    0.75
    Britain
    0.74
    Econom
    0.73
    Iraq
    0.72
    BBC
    0.72
    Prime
    0.71
     Sabha
    0.70
    Pakistan
    0.70
    Activations Density 0.097%

    No Known Activations