© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 828
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'nothing but'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "nothing but" or "more than," indicating minimalism or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.99
    pora
    -0.76
    ashington
    -0.76
    anta
    -0.75
    ¶ħ
    -0.73
    enth
    -0.73
    ulet
    -0.72
    acia
    -0.71
    glomer
    -0.70
    âĸ¬
    -0.69
    POSITIVE LOGITS
     conjecture
    0.82
     anecdotal
    0.75
     curiosity
    0.75
     vague
    0.75
     annoyance
    0.73
     silence
    0.73
     coincidence
    0.73
     superficial
    0.72
     scraps
    0.72
     mediocre
    0.71
    Activations Density 0.125%

    No Known Activations