© 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 EvalsExportsinterp-engineNEWAPI 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. 5481
    Prev
    Next
    INDEX
    Explanations

    references to and mentions of PDF documents

    oai_token-act-pair · gpt-3.5-turbo

    references to PDF documents

    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
    places
    -0.94
    dinand
    -0.81
    acha
    -0.76
    powers
    -0.75
    ffen
    -0.74
    venge
    -0.74
    allow
    -0.74
    ĪĴ
    -0.73
    inence
    -0.73
    inent
    -0.72
    POSITIVE LOGITS
    PDF
    1.18
    pdf
    1.01
     PDF
    0.91
    DragonMagazine
    0.86
     pdf
    0.84
    TeX
    0.82
    clip
    0.77
     transcript
    0.76
    clips
    0.76
     Copy
    0.74
    Activations Density 0.016%

    No Known Activations