© 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. 9-RES-JB
    11. 5253
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Ro," possibly related to a specific topic or name

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity, likely a person or place named "Ro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.78
     Brotherhood
    -0.72
     Consent
    -0.64
     Rouge
    -0.61
     Torment
    -0.61
     EntityItem
    -0.60
     occasion
    -0.60
     CPC
    -0.59
    lace
    -0.59
     Yankee
    -0.59
    POSITIVE LOGITS
    oster
    1.36
    java
    1.18
    jas
    1.08
    asted
    1.08
    zzi
    1.07
    oke
    1.06
    aches
    1.04
    aming
    1.03
    aching
    1.01
    vers
    0.99
    Activations Density 0.023%

    No Known Activations