© 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. 11-RES-JB
    11. 17667
    Prev
    Next
    INDEX
    Explanations

    negations and phrases related to absence or lack

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political or economic crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incorrectly
    -0.75
     Variant
    -0.71
    dependent
    -0.70
    alde
    -0.69
    utenberg
    -0.69
    gon
    -0.68
    hid
    -0.67
    akov
    -0.66
    ubi
    -0.66
     MISS
    -0.66
    POSITIVE LOGITS
     coherent
    1.33
     meaningful
    1.33
     substantive
    1.23
     credible
    1.21
     satisfactory
    1.18
     concerted
    1.16
     tangible
    1.13
     concrete
    1.10
     adequate
    1.10
     viable
    1.09
    Activations Density 0.475%

    No Known Activations