© 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. 10-RES-JB
    11. 16392
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "amateur" alongside various hobbies or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to amateur status or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    election
    -0.63
    grave
    -0.63
     Archdemon
    -0.62
    avorable
    -0.61
    oran
    -0.60
    metics
    -0.60
    ACTED
    -0.60
    ophers
    -0.60
    utical
    -0.59
    dos
    -0.59
    POSITIVE LOGITS
    ishly
    1.20
    ish
    1.04
    ism
    0.83
    ateur
    0.82
     astronomer
    0.81
     boxer
    0.80
     pilot
    0.77
     boxing
    0.75
     gol
    0.75
     radio
    0.74
    Activations Density 0.046%

    No Known Activations