© 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. 3-RES-JB
    11. 13939
    Prev
    Next
    INDEX
    Explanations

    mentions of large scale infrastructure projects, especially pipelines

    oai_token-act-pair · gpt-3.5-turbo

    mentions of pipelines and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.76
    orian
    -0.74
    é¾įå
    -0.73
    ilton
    -0.71
    abilia
    -0.70
    enance
    -0.70
    nesota
    -0.70
    usc
    -0.69
    evil
    -0.69
    uster
    -0.68
    POSITIVE LOGITS
     pipeline
    1.19
     pipelines
    1.17
     Pipeline
    0.92
     conduit
    0.81
    ulic
    0.80
     bottleneck
    0.79
     condu
    0.73
    soDeliveryDate
    0.73
     pipe
    0.73
    uberty
    0.73
    Activations Density 0.011%

    No Known Activations