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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17496
    Prev
    Next
    INDEX
    Explanations

    information about the author or poster of a piece of content

    oai_token-act-pair · gpt-3.5-turbo

    the word 'by' indicating authorship or attribution in the text

    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
    andise
    -0.88
    utical
    -0.84
    ãĤ½
    -0.76
    illance
    -0.73
    itialized
    -0.71
    ottesville
    -0.71
    conom
    -0.70
    ãĤ£
    -0.70
    tions
    -0.70
    Rect
    -0.69
    POSITIVE LOGITS
     Guest
    0.86
     Dustin
    0.80
     Roose
    0.76
     Brandon
    0.75
     Anonymous
    0.74
     Dave
    0.74
     STATS
    0.73
     Merry
    0.72
     POLITICO
    0.71
     Brian
    0.70
    Activations Density 0.041%

    No Known Activations