© 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. 2-RES-JB
    11. 2477
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms that indicate specific organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Birth
    -0.74
     prolific
    -0.66
    builders
    -0.64
     birth
    -0.62
     à¨
    -0.62
     Shack
    -0.61
     marrow
    -0.61
    field
    -0.60
     McDonald
    -0.60
    coded
    -0.60
    POSITIVE LOGITS
    itsch
    0.92
    kie
    0.91
    avorite
    0.90
    KK
    0.89
    erk
    0.89
    ramid
    0.89
    ANE
    0.86
    luster
    0.86
    ategory
    0.86
    anish
    0.85
    Activations Density 0.014%

    No Known Activations