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. 1-RES-JB
    6. 23791
    Prev
    Next
    INDEX
    Explanations

    the word "Is" at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Is," indicating a focus on statements or questions framed in the present tense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĮ
    -0.76
    ð
    -0.70
    è¦ļéĨĴ
    -0.69
    å§«
    -0.69
    èª
    -0.68
    è£
    -0.67
    åij
    -0.66
    IOR
    -0.65
    å§
    -0.65
    Poké
    -0.64
    POSITIVE LOGITS
    olated
    1.18
    olate
    1.12
    ync
    1.10
    olation
    1.07
    sei
    1.01
    abella
    0.99
    htar
    0.90
    nt
    0.88
    peria
    0.87
    rael
    0.86
    Activations Density 0.019%

    No Known Activations