© 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. 9-RES-JB
    11. 18570
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or events happening in different places

    oai_token-act-pair · gpt-3.5-turbo

    references to activities or events occurring in specific locations or times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
    ãĥīãĥ©
    -0.76
     issu
    -0.71
    soever
    -0.68
     altogether
    -0.67
    INAL
    -0.66
     definitively
    -0.65
    politics
    -0.65
    Process
    -0.64
     arrang
    -0.64
    POSITIVE LOGITS
     Buenos
    0.80
     his
    0.77
     Chinatown
    0.77
     nearby
    0.75
     Chattanooga
    0.74
     Cornwall
    0.73
     Georgetown
    0.73
     disguise
    0.73
     Seoul
    0.73
     Marin
    0.72
    Activations Density 0.417%

    No Known Activations