© 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. 19419
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions taken towards others

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating significant actions or events

    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
     ][
    -0.71
    ortium
    -0.67
    adelphia
    -0.66
    ibrary
    -0.64
    esa
    -0.64
    ÃŃn
    -0.63
    reshold
    -0.62
    yne
    -0.62
    arel
    -0.62
    rez
    -0.62
    POSITIVE LOGITS
     accordingly
    1.25
     alike
    0.93
     consequently
    0.88
     thereafter
    0.81
     himself
    0.75
     therein
    0.75
     afterward
    0.74
     thereby
    0.72
     therefore
    0.72
     herself
    0.72
    Activations Density 0.339%

    No Known Activations