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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15905
    Prev
    Next
    INDEX
    Explanations

    phrases that transition between topics or points in a text

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" to connect various ideas or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ses
    -0.71
    sk
    -0.70
    fur
    -0.67
    fell
    -0.67
    pees
    -0.65
    arthed
    -0.65
    duct
    -0.65
    series
    -0.65
    ://
    -0.64
    ãģĨ
    -0.63
    POSITIVE LOGITS
    romeda
    1.11
     furthermore
    1.06
    hra
    1.03
     secondly
    0.98
    rea
    0.97
     moreover
    0.93
     consequently
    0.90
     therefore
    0.89
    alus
    0.88
     therein
    0.86
    Activations Density 0.078%

    No Known Activations