© 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. 7-RES-JB
    11. 18713
    Prev
    Next
    INDEX
    Explanations

    words related to books, sports, and technology

    oai_token-act-pair · gpt-3.5-turbo

    single characters or letters that represent key elements in the text

    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
    EStream
    -0.70
     respons
    -0.69
     Vera
    -0.66
     refrain
    -0.66
     annexed
    -0.65
     chau
    -0.62
     boycot
    -0.62
     ana
    -0.62
     phased
    -0.61
     dere
    -0.61
    POSITIVE LOGITS
    acker
    1.02
    uffs
    1.01
    ackers
    1.00
    orts
    0.99
    akes
    0.98
    igs
    0.97
    ights
    0.97
    ricks
    0.97
    reens
    0.96
    icks
    0.96
    Activations Density 0.130%

    No Known Activations