© 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. 1-RES-JB
    11. 8836
    Prev
    Next
    INDEX
    Explanations

    terms related to metadata or sections within a document

    oai_token-act-pair · gpt-3.5-turbo

    terms related to referencing previous content or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.70
    park
    -0.69
    hof
    -0.66
     dot
    -0.66
     Nut
    -0.65
     ware
    -0.64
    kamp
    -0.63
     peanuts
    -0.63
     gems
    -0.63
    RF
    -0.62
    POSITIVE LOGITS
    Previous
    1.35
     Previous
    1.27
     millenn
    0.86
    Prev
    0.86
    terior
    0.85
    ĸļ
    0.81
    vier
    0.81
    heastern
    0.80
     Flavoring
    0.79
    ¥ŀ
    0.78
    Activations Density 0.004%

    No Known Activations