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. 22867
    Prev
    Next
    INDEX
    Explanations

    phrases intensifying an adjective

    oai_token-act-pair · gpt-3.5-turbo

    repetitive use of the word "very" with varying levels of intensity

    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
     sts
    -0.66
    ãĤ´
    -0.62
     Camel
    -0.59
     Mansion
    -0.59
    ãĥĩ
    -0.59
     guiActiveUn
    -0.58
     Citiz
    -0.58
     Cato
    -0.57
     redes
    -0.55
     hither
    -0.55
    POSITIVE LOGITS
    ceptor
    0.87
     uh
    0.79
     yeah
    0.77
    certain
    0.76
     um
    0.72
    ties
    0.72
    kward
    0.70
    cientious
    0.70
     albeit
    0.69
    cellent
    0.68
    Activations Density 0.174%

    No Known Activations