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. 4-RES-JB
    6. 12963
    Prev
    Next
    INDEX
    Explanations

    the word "ips."

    oai_token-act-pair · gpt-3.5-turbo

    references to "ips" or related suffixes

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

    No Comments

    Negative Logits
     Aval
    -0.70
    WAYS
    -0.68
     damned
    -0.68
    scape
    -0.67
    mates
    -0.65
    WAY
    -0.65
     Saud
    -0.65
     Defin
    -0.63
     volumes
    -0.62
    \\\\\\\\\\\\\\\\
    -0.62
    POSITIVE LOGITS
    etsk
    1.04
    ips
    1.03
    ilateral
    1.03
    aret
    1.02
    awed
    1.01
    ilon
    0.99
    olitan
    0.98
    hift
    0.98
    ilver
    0.97
    creen
    0.96
    Activations Density 0.010%

    No Known Activations