© 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. 9-RES-JB
    6. 13247
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational structures or business strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate multi-faceted or multi-dimensional concepts

    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
     Lans
    -0.72
     Richards
    -0.68
     Boxing
    -0.68
     Finch
    -0.68
     Rab
    -0.68
     Hoo
    -0.67
     Lee
    -0.67
     Reed
    -0.67
     Junk
    -0.65
     Klaus
    -0.65
    POSITIVE LOGITS
    dimensional
    1.44
    purpose
    1.28
    disciplinary
    1.27
    ethnic
    1.22
    functional
    1.21
    sided
    1.20
    task
    1.18
    direction
    1.17
    national
    1.16
    colored
    1.16
    Activations Density 0.028%

    No Known Activations