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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 7913
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations, companies, or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and news agency references

    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
    :\
    -0.76
    plet
    -0.71
     accur
    -0.71
     cuff
    -0.70
     capacities
    -0.67
    lear
    -0.66
    chairs
    -0.66
    aples
    -0.64
    ulously
    -0.63
    :]
    -0.63
    POSITIVE LOGITS
     Morg
    0.69
     Ltd
    0.68
     meanwhile
    0.66
    Ħ¢
    0.65
     Mons
    0.65
    Laun
    0.65
     which
    0.63
     Avalon
    0.63
    Instance
    0.62
     Zionism
    0.61
    Activations Density 0.379%

    No Known Activations