© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    words related to the letter "o" with certain conditions, such as being surrounded by other specific characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'o'

    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
     Yel
    -0.66
     Staples
    -0.66
     Buckley
    -0.63
     subjects
    -0.59
     Irma
    -0.59
     Lambert
    -0.59
     Painter
    -0.58
     equ
    -0.56
     index
    -0.56
     IF
    -0.55
    POSITIVE LOGITS
    phthal
    1.30
    atmeal
    1.29
    lymp
    1.21
    mbudsman
    1.19
    cular
    1.18
    liv
    1.18
    regon
    1.16
    vals
    1.15
    mitting
    1.15
    asis
    1.15
    Activations Density 0.020%

    No Known Activations