© 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. 1-RES-JB
    11. 6682
    Prev
    Next
    INDEX
    Explanations

    words related to rising, advancing, or progressing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rising or increasing status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ò
    -0.75
    FactoryReloaded
    -0.74
     Hart
    -0.73
    VICE
    -0.70
     Grab
    -0.67
     Reloaded
    -0.67
     Hearts
    -0.67
     Goo
    -0.66
     Cross
    -0.66
     Muse
    -0.65
    POSITIVE LOGITS
     asc
    1.28
    endant
    1.24
    ribed
    1.23
     mathemat
    1.15
     ascend
    1.10
    ension
    1.10
     ascent
    1.08
    olesc
    1.05
    orns
    1.02
    ribing
    1.00
    Activations Density 0.004%

    No Known Activations