© 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. 8-RES-JB
    11. 10865
    Prev
    Next
    INDEX
    Explanations

    phrases related to aiding in adjustment and thriving after a significant event like military service or in societal settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LOG
    -0.74
    killed
    -0.69
     lodged
    -0.68
    username
    -0.63
     began
    -0.62
    released
    -0.61
    CVE
    -0.59
     %%
    -0.59
     introduced
    -0.59
    ouf
    -0.59
    POSITIVE LOGITS
     lieu
    1.36
     spite
    1.32
     regards
    1.25
     terms
    1.21
     relation
    1.19
     accordance
    1.17
     conjunction
    1.05
    ordinate
    1.04
    animate
    1.04
     unison
    1.01
    Activations Density 0.409%

    No Known Activations