© 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. 8-RES-JB
    11. 23877
    Prev
    Next
    INDEX
    Explanations

    terms related to academic institutions or colleges

    oai_token-act-pair · gpt-3.5-turbo

    references to academic colleges and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vati
    -0.72
     blacklist
    -0.71
    chev
    -0.67
     clust
    -0.66
    XM
    -0.65
     overrun
    -0.63
    etsk
    -0.60
     impuls
    -0.60
    ĸļ
    -0.60
     hoard
    -0.60
    POSITIVE LOGITS
    lege
    0.98
    course
    0.73
    lear
    0.73
    orts
    0.72
     Engineers
    0.71
    operative
    0.69
    sylvania
    0.68
     Arts
    0.67
    ople
    0.67
    ishops
    0.67
    Activations Density 0.079%

    No Known Activations