© 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. 17163
    Prev
    Next
    INDEX
    Explanations

    specific instances or situations where something is set aside or allocated for a particular purpose

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "reserved."

    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
    dj
    -0.72
    enegger
    -0.70
    ymes
    -0.69
    kok
    -0.68
    akeru
    -0.67
    externalActionCode
    -0.67
    utra
    -0.67
     Shutterstock
    -0.66
    pson
    -0.61
    ODE
    -0.61
    POSITIVE LOGITS
    ateurs
    0.92
     reserved
    0.80
    rete
    0.80
     seating
    0.80
     seats
    0.78
     glances
    0.78
    ately
    0.77
    inence
    0.75
    entric
    0.74
    rals
    0.73
    Activations Density 0.034%

    No Known Activations