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. 9753
    Prev
    Next
    INDEX
    Explanations

    phrases related to pointing out or emphasizing specific information

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" 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
    rete
    -0.81
    Course
    -0.75
    icking
    -0.69
    istics
    -0.69
    iscover
    -0.68
    register
    -0.66
    Laughs
    -0.66
    fect
    -0.65
    oleon
    -0.65
    arak
    -0.64
    POSITIVE LOGITS
     justifies
    1.19
     accompanies
    1.19
     contradicts
    1.18
     proves
    1.13
     suggests
    1.11
     undermines
    1.08
     resulted
    1.05
     contradicted
    1.01
     indicates
    1.00
     prevailed
    0.98
    Activations Density 0.137%

    No Known Activations