© 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. 22632
    Prev
    Next
    INDEX
    Explanations

    names of individuals consisting of multiple parts or hyphenated names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in notable incidents or events

    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
     FANTASY
    -0.83
     archived
    -0.60
     NFC
    -0.59
     IDE
    -0.57
     circular
    -0.57
     Millennials
    -0.56
    atform
    -0.55
    Disclaimer
    -0.54
     polarized
    -0.53
     deduction
    -0.53
    POSITIVE LOGITS
    iani
    0.76
     Jr
    0.75
    oso
    0.73
    ovich
    0.72
    cko
    0.72
    iewicz
    0.72
    isi
    0.71
     III
    0.71
    anski
    0.69
    opoulos
    0.69
    Activations Density 0.526%

    No Known Activations