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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 15894
    Prev
    Next
    INDEX
    Explanations

    verbs in the form of 'to be' or 'to have'

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements or claims about conditions and possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.80
    luaj
    -0.76
    ONSORED
    -0.69
    iatus
    -0.65
    EStream
    -0.64
    ipal
    -0.63
    iba
    -0.62
    arthed
    -0.62
    untled
    -0.62
    endar
    -0.60
    POSITIVE LOGITS
     important
    1.13
     imperative
    1.13
     crucial
    1.09
     invaluable
    1.08
     easier
    1.08
     MUCH
    1.04
     priceless
    1.03
     usually
    1.03
     harder
    1.03
     vital
    1.03
    Activations Density 0.259%

    No Known Activations