Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14336
    Prev
    Next
    INDEX
    Explanations

    the word "right" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "right" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RESULTS
    -0.66
     Cannot
    -0.64
     Mechdragon
    -0.64
     Ibid
    -0.60
    ously
    -0.59
     Deaths
    -0.58
    kel
    -0.58
    agos
    -0.57
    ega
    -0.57
    ATA
    -0.56
    POSITIVE LOGITS
     right
    3.46
     RIGHT
    2.84
    right
    2.60
     Right
    2.54
    Right
    2.40
     wrong
    1.54
     correct
    1.52
     left
    1.46
    left
    1.33
    wrong
    1.30
    Activations Density 0.049%

    No Known Activations