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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 18791
    Prev
    Next
    INDEX
    Explanations

    terms related to historical events and economic analysis

    oai_token-act-pair · gpt-3.5-turbo

    discussions surrounding historical and economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.53
    arms
    -0.53
    pload
    -0.52
    iggins
    -0.52
    nor
    -0.51
    tch
    -0.51
    raper
    -0.50
     caveat
    -0.50
    *.
    -0.49
    pleting
    -0.48
    POSITIVE LOGITS
     transgender
    0.52
     microbiome
    0.50
     NBN
    0.50
     Zionism
    0.49
     finances
    0.48
     misconceptions
    0.46
     warfare
    0.46
    âĢİ
    0.46
     metab
    0.46
     differently
    0.46
    Activations Density 1.352%

    No Known Activations