© 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. 0-RES-JB
    11. 1094
    Prev
    Next
    INDEX
    Explanations

    terms related to significant actions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to "ages" or terms related to age distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     registry
    -0.64
     degree
    -0.62
    EStream
    -0.60
     fit
    -0.59
     soundtrack
    -0.57
     compliant
    -0.57
     nucleus
    -0.55
     coron
    -0.55
     Presidential
    -0.54
     Deputy
    -0.54
    POSITIVE LOGITS
    ages
    4.92
    age
    3.25
    AGES
    2.88
    aged
    2.78
    AGE
    2.73
    aging
    2.71
    agers
    2.29
    agement
    1.81
    ager
    1.73
    agements
    1.66
    Activations Density 0.004%

    No Known Activations