© 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. 14554
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to activities or tasks being done

    oai_token-act-pair · gpt-3.5-turbo

    references to personal and professional experiences

    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
     notwithstanding
    -0.71
     solved
    -0.65
     exacerbated
    -0.65
    00007
    -0.65
     Nanto
    -0.62
    ¶ħ
    -0.62
     insofar
    -0.61
    ģĸ
    -0.58
    enance
    -0.58
     Krish
    -0.58
    POSITIVE LOGITS
    gil
    0.69
    enium
    0.68
    uberty
    0.67
    ascus
    0.64
    azeera
    0.63
    robe
    0.63
    QUEST
    0.62
    essim
    0.61
    rament
    0.61
    DIT
    0.61
    Activations Density 0.775%

    No Known Activations