© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21746
    Prev
    Next
    INDEX
    Explanations

    divisions or categories in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of categorization or classification

    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
    stocks
    -0.78
    '"
    -0.67
    cour
    -0.67
    stock
    -0.66
    hesda
    -0.65
    Nintendo
    -0.65
    Ãį
    -0.65
    brew
    -0.63
    ournals
    -0.61
    Documents
    -0.61
    POSITIVE LOGITS
    mbuds
    0.72
     Gle
    0.71
    VK
    0.68
     isot
    0.67
     pige
    0.66
     antidepress
    0.63
     unsigned
    0.62
     Lil
    0.61
    inel
    0.60
     Mit
    0.59
    Activations Density 0.278%

    No Known Activations