© 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. 2-RES-JB
    11. 24022
    Prev
    Next
    INDEX
    Explanations

    terms related to latency issues and timeouts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to latency and time delays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -1.05
    adra
    -0.86
    ning
    -0.80
    atically
    -0.80
    bu
    -0.79
    ulating
    -0.79
    alore
    -0.79
    acles
    -0.77
    agall
    -0.77
    ril
    -0.76
    POSITIVE LOGITS
     latency
    1.17
     milliseconds
    0.86
     cumbers
    0.79
    BILITY
    0.78
     lapse
    0.70
     TTL
    0.69
    Todd
    0.66
     inacc
    0.65
     vulner
    0.65
     timeout
    0.64
    Activations Density 0.023%

    No Known Activations