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. 7-RES-JB
    6. 16567
    Prev
    Next
    INDEX
    Explanations

    phrases related to updates or changes on websites

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "have"

    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
    accompan
    -0.65
     Niet
    -0.64
     drafting
    -0.61
     Allied
    -0.61
    oppable
    -0.60
     territ
    -0.58
     Inquisition
    -0.57
     nearest
    -0.56
     vulner
    -0.56
     contrace
    -0.55
    POSITIVE LOGITS
     been
    0.97
     WATCHED
    0.82
    been
    0.78
     emerged
    0.75
     reached
    0.72
    bara
    0.71
    kell
    0.71
     begun
    0.70
    zbollah
    0.67
     gotten
    0.66
    Activations Density 0.039%

    No Known Activations