© 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. 8761
    Prev
    Next
    INDEX
    Explanations

    phrases describing contrast or opposition

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or statements

    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
    opher
    -0.74
     metic
    -0.73
     suspic
    -0.72
    hea
    -0.70
     shifts
    -0.69
     compens
    -0.68
    pell
    -0.68
     preference
    -0.67
     sore
    -0.67
     subsequ
    -0.67
    POSITIVE LOGITS
    _-
    1.47
    âĢ¢âĢ¢
    1.09
    =-=-=-=-
    1.09
    âĸº
    0.95
     [|
    0.88
    webkit
    0.87
    /-
    0.85
     Advertisement
    0.85
    =-=-=-=-=-=-=-=-
    0.83
    ––
    0.81
    Activations Density 0.060%

    No Known Activations