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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17783
    Prev
    Next
    INDEX
    Explanations

    contractions

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms of "is" used to express statements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isively
    -0.70
    atively
    -0.68
    lessly
    -0.66
    riors
    -0.66
    ially
    -0.66
    velop
    -0.65
    sters
    -0.64
     resumes
    -0.63
    nesses
    -0.63
    ievers
    -0.63
    POSITIVE LOGITS
     gonna
    1.02
     gotta
    0.98
    IELD
    0.79
     Mahjong
    0.76
     been
    0.75
    pace
    0.73
     Been
    0.70
    ãĤ°
    0.67
    SPONSORED
    0.67
     got
    0.66
    Activations Density 0.038%

    No Known Activations