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. 1-RES-JB
    6. 12744
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing the importance or inclusivity of various aspects in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "everything" in various contexts

    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
    ker
    -0.82
    bal
    -0.77
    ste
    -0.70
    jac
    -0.67
     Peninsula
    -0.66
    hold
    -0.64
    steen
    -0.63
    kers
    -0.63
    eder
    -0.63
    inst
    -0.62
    POSITIVE LOGITS
     else
    1.25
     imaginable
    1.18
    THING
    1.09
    Else
    1.00
     conceivable
    0.92
    igator
    0.86
     proport
    0.84
     happens
    0.80
     sorts
    0.80
     Else
    0.78
    Activations Density 0.017%

    No Known Activations