© 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. 3690
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "opposite."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "opposite."

    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
    adows
    -0.79
    beans
    -0.78
     Annotations
    -0.78
    ulic
    -0.77
    urrent
    -0.76
    uay
    -0.73
    din
    -0.72
     Beans
    -0.72
    haw
    -0.72
    utters
    -0.72
    POSITIVE LOGITS
     sexes
    0.99
     sides
    0.96
     side
    0.89
     gender
    0.86
     sex
    0.84
     extremes
    0.82
    osite
    0.78
     hemisphere
    0.76
     direction
    0.76
     genders
    0.75
    Activations Density 0.042%

    No Known Activations