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. 10-RES-JB
    6. 16771
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'only' followed by a noun or prepositional phrase

    oai_token-act-pair · gpt-3.5-turbo

    the word "only" and its context in phrases indicating limitation or exclusivity

    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
    cent
    -0.68
    desc
    -0.65
    insula
    -0.65
    MAP
    -0.64
    mos
    -0.62
    atana
    -0.62
    aviour
    -0.61
    alam
    -0.61
    pad
    -0.60
    bell
    -0.59
    POSITIVE LOGITS
     fitting
    1.14
     natural
    0.93
     logical
    0.89
     fair
    0.81
     prudent
    0.80
    ifiable
    0.73
     conceivable
    0.73
     downhill
    0.71
     uphill
    0.71
     fractions
    0.70
    Activations Density 0.050%

    No Known Activations