© 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. 24013
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or URLs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating clickable links or calls to action

    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
     amput
    -0.84
    etheless
    -0.79
    SPONSORED
    -0.76
     manslaughter
    -0.72
     suff
    -0.70
    bage
    -0.67
     idol
    -0.66
    deen
    -0.66
     himself
    -0.66
     Anglic
    -0.65
    POSITIVE LOGITS
     Refresh
    0.79
     Pastebin
    0.76
    66666666
    0.71
    ++++
    0.69
     Raspberry
    0.69
     Logo
    0.68
     QR
    0.68
     VIDEOS
    0.66
    âĸ¬
    0.66
     TBD
    0.66
    Activations Density 3.275%

    No Known Activations