© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11325
    Prev
    Next
    INDEX
    Explanations

    the string "omm" with varying following characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "comm" likely in references to communication, committees, or community-related contexts

    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
    ting
    -0.88
    ted
    -0.87
    footed
    -0.71
    BOOK
    -0.71
    JUST
    -0.68
     bowl
    -0.66
     BDS
    -0.65
     Hindus
    -0.64
    ======
    -0.64
    TING
    -0.62
    POSITIVE LOGITS
    omm
    1.32
    ittee
    1.16
    orrow
    1.12
    essage
    1.11
    obile
    1.09
     arrang
    1.03
     confir
    0.99
    ortal
    0.96
    mares
    0.94
     comr
    0.93
    Activations Density 0.004%

    No Known Activations