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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8780
    Prev
    Next
    INDEX
    Explanations

    the verb "is" at the beginning of statements

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there is" in various contexts

    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
    ares
    -0.80
    iaries
    -0.61
    ends
    -0.61
     cylinders
    -0.60
    olds
    -0.60
     approves
    -0.60
    enth
    -0.60
     retrie
    -0.60
    doms
    -0.60
    isms
    -0.59
    POSITIVE LOGITS
     nothing
    1.11
     plenty
    1.09
     ample
    1.06
     no
    1.06
     always
    0.99
     nowhere
    0.98
     ALWAYS
    0.92
     something
    0.92
     definitely
    0.92
     nobody
    0.89
    Activations Density 0.109%

    No Known Activations