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. 20157
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    the names of individuals and related references in various contexts

    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
     awa
    -0.57
    rium
    -0.57
    ggle
    -0.54
    farious
    -0.54
    -+-+
    -0.53
    chnology
    -0.51
    Loading
    -0.51
    sylv
    -0.50
    Grade
    -0.49
    romeda
    -0.48
    POSITIVE LOGITS
     notwithstanding
    0.57
     è£ıè
    0.56
    )?
    0.53
     auto
    0.48
     adv
    0.48
     Preferred
    0.47
     replies
    0.47
    !--
    0.47
     replied
    0.46
    ¶
    0.46
    Activations Density 1.044%

    No Known Activations