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

    Neuronpedia

    Jacobian LensNEW
    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. 1930
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical structures or formations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating abundance or quantity

    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
    acus
    -0.80
     stride
    -0.72
    oking
    -0.70
    hra
    -0.69
    riber
    -0.68
    century
    -0.68
    jad
    -0.68
    tarians
    -0.67
    ibe
    -0.67
    bowl
    -0.66
    POSITIVE LOGITS
     sorts
    1.28
     goodies
    0.86
     assorted
    0.77
     pixels
    0.75
     extras
    0.74
     colorful
    0.74
     disparate
    0.74
     stars
    0.72
     rubble
    0.71
     seats
    0.70
    Activations Density 0.122%

    No Known Activations