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. 0-RES-JB
    6. 3884
    Prev
    Next
    INDEX
    Explanations

    mentions of physical tightness or constraints

    oai_token-act-pair · gpt-3.5-turbo

    the term "tight" 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
    Footnote
    -0.82
    enges
    -0.74
    DragonMagazine
    -0.70
    DR
    -0.67
    eeds
    -0.67
    opathic
    -0.66
     Amph
    -0.65
    ITNESS
    -0.65
    arma
    -0.65
    mol
    -0.64
    POSITIVE LOGITS
     tight
    3.75
     Tight
    2.52
    tight
    2.38
     tighter
    2.35
     tightly
    1.87
     tightened
    1.61
     snug
    1.58
     tightening
    1.51
     tighten
    1.44
     loose
    1.28
    Activations Density 0.009%

    No Known Activations