© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12447
    Prev
    Next
    INDEX
    Explanations

    phrases related to different states or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of a state or condition, particularly using the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dad
    -0.72
    iest
    -0.70
    azines
    -0.66
    falls
    -0.66
    prints
    -0.64
    bones
    -0.63
     EntityItem
    -0.61
    ials
    -0.59
    paces
    -0.59
    iaries
    -0.58
    POSITIVE LOGITS
     sorts
    1.23
     theirs
    0.82
     hers
    0.72
     attrition
    0.70
     heightened
    0.69
     exclus
    0.69
     ours
    0.69
    ãĥİ
    0.68
     unparalleled
    0.67
     reckoning
    0.67
    Activations Density 0.183%

    No Known Activations