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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 12965
    Prev
    Next
    INDEX
    Explanations

    adverbs and adverbial phrases

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÂŃ
    -0.78
    SPONSORED
    -0.74
     è£ıç
    -0.71
    ogenic
    -0.69
    ê
    -0.69
    cedented
    -0.69
     Guant
    -0.67
    ],"
    -0.65
     Mehran
    -0.65
    WASHINGTON
    -0.65
    POSITIVE LOGITS
     honestly
    0.87
     downside
    0.79
     hindsight
    0.78
     glim
    0.75
    Anyway
    0.75
     blat
    0.75
     furthermore
    0.74
     apologies
    0.74
     classy
    0.73
    Honestly
    0.72
    Activations Density 0.639%

    No Known Activations