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. 17421
    Prev
    Next
    INDEX
    Explanations

    verbs related to work or actions in specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups involved in action or decision-making

    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
     spoilers
    -0.78
    Else
    -0.75
     spoiler
    -0.69
    Rober
    -0.66
     Pere
    -0.66
     Kush
    -0.64
     Pun
    -0.63
    theless
    -0.60
    oiler
    -0.59
     Forth
    -0.59
    POSITIVE LOGITS
     destined
    0.75
    ée
    0.73
     dearly
    0.72
    ufact
    0.70
    ãĥ¼ãĥĨ
    0.68
    atel
    0.64
     inhabit
    0.63
    ãĤ©
    0.62
    ba
    0.62
    ·
    0.61
    Activations Density 0.284%

    No Known Activations