© 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. 4-RES-JB
    11. 23986
    Prev
    Next
    INDEX
    Explanations

    configurations or settings in a text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to configuration settings in a technical context

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

    No Comments

    Negative Logits
     Flavoring
    -0.87
     Gael
    -0.81
    FORE
    -0.77
    Downloadha
    -0.75
     Mata
    -0.74
    deen
    -0.71
     Apost
    -0.70
     Antiqu
    -0.70
     Karen
    -0.68
    theless
    -0.68
    POSITIVE LOGITS
    urations
    1.53
    uration
    1.47
    urable
    1.46
    uring
    1.21
    urated
    1.19
    ured
    1.17
    urer
    1.17
    ure
    1.08
    isters
    1.02
    urers
    1.00
    Activations Density 0.011%

    No Known Activations