© 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. 11-RES-JB
    11. 1467
    Prev
    Next
    INDEX
    Explanations

    words related to written text and letters

    oai_token-act-pair · gpt-3.5-turbo

    references to letters and their characteristics in written language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roxy
    -0.93
    Kin
    -0.79
    ONSORED
    -0.77
    ouf
    -0.75
     srfAttach
    -0.73
    IED
    -0.72
    ^^^^
    -0.72
     Cros
    -0.68
    Laun
    -0.67
     Darling
    -0.66
    POSITIVE LOGITS
     alphabet
    1.24
    acters
    1.16
     abbrevi
    1.05
     pronunciation
    1.04
     notation
    1.02
     prefix
    1.02
     suffix
    1.00
     abbre
    0.98
    ames
    0.97
     spelling
    0.97
    Activations Density 0.128%

    No Known Activations