© 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. 1-RES-JB
    11. 3286
    Prev
    Next
    INDEX
    Explanations

    verbs related to enhancing or improving something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "strengthen" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marathon
    -0.75
     Arcade
    -0.73
     Columb
    -0.72
     Crowley
    -0.72
    erenn
    -0.69
    FACE
    -0.66
     Sloan
    -0.66
     Warcraft
    -0.65
     Mamm
    -0.65
     Gorge
    -0.64
    POSITIVE LOGITS
     strengthening
    1.14
     tremend
    1.13
     strengthen
    1.13
     streng
    1.08
     guiActiveUn
    0.96
     strengthens
    0.91
     undermin
    0.91
    thening
    0.90
    ieth
    0.90
     misunder
    0.90
    Activations Density 0.012%

    No Known Activations