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. 11-RES-JB
    6. 10346
    Prev
    Next
    INDEX
    Explanations

    the phrase "on the other hand"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "on the other hand"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regor
    -0.69
    umers
    -0.61
    bourg
    -0.61
     unfocusedRange
    -0.59
     bom
    -0.59
    ibur
    -0.59
    ITED
    -0.58
    å§«
    -0.58
    atron
    -0.58
    RED
    -0.56
    POSITIVE LOGITS
     hand
    1.75
    hand
    1.32
     side
    1.28
     cheek
    1.16
     paw
    1.09
    side
    1.04
     hands
    1.02
     sleeve
    0.99
    Hand
    0.99
     Hand
    0.99
    Activations Density 0.029%

    No Known Activations