© 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. 13532
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a situation or event happening in the midst of something else

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "amid" or phrases indicating ongoing situations or circumstances

    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
    ordan
    -0.75
    ubuntu
    -0.69
    iability
    -0.65
    iotic
    -0.64
    768
    -0.61
     Mehran
    -0.60
    irs
    -0.60
    ared
    -0.60
    abulary
    -0.60
    farious
    -0.60
    POSITIVE LOGITS
     amidst
    0.89
     amid
    0.88
    ĸļ
    0.87
    )=(
    0.83
    terness
    0.79
    Īè
    0.78
     showc
    0.76
    IJ
    0.76
     Mania
    0.71
    ãĤ´ãĥ³
    0.70
    Activations Density 0.005%

    No Known Activations