© 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. 2-RES-JB
    11. 12697
    Prev
    Next
    INDEX
    Explanations

    words related to printed materials like brochures, pamphlets, and booklets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to printed materials or informational documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alez
    -0.71
    alty
    -0.69
    ths
    -0.67
    haul
    -0.67
    oln
    -0.66
     Valley
    -0.66
    agara
    -0.64
    esse
    -0.64
    itutional
    -0.63
    pine
    -0.63
    POSITIVE LOGITS
     pamph
    1.16
     pamphlet
    1.10
     flyer
    1.01
     booklet
    0.95
     broch
    0.88
     leaflets
    0.87
    lete
    0.77
    let
    0.75
    lets
    0.74
     Niet
    0.74
    Activations Density 0.017%

    No Known Activations