© 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. 11-RES-JB
    11. 18832
    Prev
    Next
    INDEX
    Explanations

    references to the name "Rom"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Rom," possibly signifying an interest in a specific subject or character related to that term

    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
     grounds
    -0.67
     cursor
    -0.64
     herds
    -0.60
     dams
    -0.59
     Wasteland
    -0.59
     CPC
    -0.59
     presiding
    -0.58
     Marshal
    -0.57
     Lotus
    -0.56
     traveller
    -0.56
    POSITIVE LOGITS
    antically
    1.41
    antics
    1.33
    ulus
    1.29
    ijn
    1.17
    anes
    1.17
    agna
    1.17
    aji
    1.17
    antic
    1.16
    ances
    1.13
    aine
    1.12
    Activations Density 0.044%

    No Known Activations