© 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. 17589
    Prev
    Next
    INDEX
    Explanations

    cryptic or encoded text patterns

    oai_token-act-pair · gpt-3.5-turbo

    repeated sequences of special characters or patterns

    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
     Peb
    -0.90
     strap
    -0.69
     orbit
    -0.67
     Prairie
    -0.64
     range
    -0.64
     Ridley
    -0.63
     scope
    -0.63
     barrier
    -0.60
     portable
    -0.60
     bracelet
    -0.60
    POSITIVE LOGITS
    ————
    1.32
    ——
    1.31
    —-
    1.23
    ————————
    1.03
    >>>
    0.98
    ————————————————
    0.97
    Lenin
    0.95
    ––
    0.91
    ãĤ¦ãĤ¹
    0.91
    DOWN
    0.90
    Activations Density 0.008%

    No Known Activations