© 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. 9546
    Prev
    Next
    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Stefan or Klaus

    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
    BACK
    -0.74
    REE
    -0.70
    rights
    -0.69
    outh
    -0.66
     Indians
    -0.65
    lled
    -0.64
    naire
    -0.64
    nces
    -0.62
    upon
    -0.62
    hazard
    -0.61
    POSITIVE LOGITS
     Stefan
    1.21
    stadt
    0.98
    ovic
    0.87
    etti
    0.82
    apo
    0.80
    acci
    0.79
    ucci
    0.77
     Rah
    0.77
     Matte
    0.76
     Stef
    0.75
    Activations Density 0.008%

    No Known Activations