© 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. 24032
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "old."

    oai_token-act-pair · gpt-3.5-turbo

    references to something that is considered old or outdated

    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
     sclerosis
    -0.77
    rawdownloadcloneembedreportprint
    -0.73
     immediate
    -0.68
    çīĪ
    -0.68
    vous
    -0.68
     teasp
    -0.67
     charism
    -0.67
    pload
    -0.67
     Shutterstock
    -0.67
     ILCS
    -0.66
    POSITIVE LOGITS
    rums
    1.05
    old
    0.97
    est
    0.94
    sworth
    0.87
    mort
    0.84
    ishly
    0.80
    enburg
    0.79
    swick
    0.78
     fashioned
    0.78
    face
    0.78
    Activations Density 0.011%

    No Known Activations