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. 11-RES-JB
    6. 16839
    Prev
    Next
    INDEX
    Explanations

    the phrase "sort of"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "sort of" in various contexts

    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
     TAM
    -0.62
     Mississ
    -0.61
    VIS
    -0.60
    PLIC
    -0.60
     Madison
    -0.59
     Dent
    -0.57
     Milan
    -0.57
    PER
    -0.55
    ELL
    -0.54
     Confederation
    -0.53
    POSITIVE LOGITS
    a
    1.12
    of
    0.94
    ilege
    0.84
     of
    0.83
     thereof
    0.83
    erest
    0.82
    Of
    0.80
    ative
    0.79
    able
    0.79
    ies
    0.79
    Activations Density 0.030%

    No Known Activations