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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 7-RES-JB
    6. 10602
    Prev
    Next
    INDEX
    Explanations

    expressions containing the word "think"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "if you think."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iona
    -0.79
    kw
    -0.74
    clad
    -0.73
    yna
    -0.68
    announced
    -0.67
    accompanied
    -0.65
    acerb
    -0.65
    çĦ
    -0.63
    Naz
    -0.63
    SPONSORED
    -0.62
    POSITIVE LOGITS
     about
    0.78
     differently
    0.74
     alike
    0.68
     aloud
    0.68
     it
    0.67
    orial
    0.66
     bout
    0.66
     provoking
    0.66
    phis
    0.66
     wrongly
    0.65
    Activations Density 0.074%

    No Known Activations