© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 11496
    Prev
    Next
    INDEX
    Explanations

    mentions of a debut or debut-related activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "debut" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bara
    -0.67
    akia
    -0.66
    chn
    -0.66
    nsic
    -0.64
    tics
    -0.63
    apons
    -0.62
    pe
    -0.62
     annexed
    -0.61
    tti
    -0.61
     abused
    -0.60
    POSITIVE LOGITS
    antes
    1.13
    ante
    0.99
    antly
    0.85
    iour
    0.82
    interstitial
    0.76
    iator
    0.76
    éĹĺ
    0.75
     foray
    0.75
     debut
    0.75
    iary
    0.74
    Activations Density 0.027%

    No Known Activations