Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 237
    Prev
    Next
    INDEX
    Explanations

    opportunities or chances to do something

    oai_token-act-pair · gpt-3.5-turbo

    opportunities or instances of having a chance to participate in events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blames
    -0.75
     endif
    -0.75
     punishable
    -0.74
     endanger
    -0.71
     denies
    -0.71
     blaming
    -0.70
     withdrawn
    -0.69
    $$$$
    -0.67
    endif
    -0.65
     hurting
    -0.64
    POSITIVE LOGITS
     myself
    0.92
     fortunate
    0.87
     firsthand
    0.86
     chatting
    0.80
     preview
    0.77
    displayText
    0.77
     interviewing
    0.75
     browsing
    0.74
     reader
    0.73
    onnaissance
    0.73
    Activations Density 0.412%

    No Known Activations