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. 9-RES-JB
    6. 9798
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express capability or possibility

    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
     Adin
    -0.66
     Respons
    -0.65
     Returning
    -0.64
     RELE
    -0.63
     forthcoming
    -0.63
     airs
    -0.61
    members
    -0.61
    Required
    -0.61
     Attention
    -0.60
     duties
    -0.60
    POSITIVE LOGITS
     imagine
    1.24
     argue
    1.14
    't
    1.09
     see
    1.04
     expect
    1.02
     hear
    0.99
     bet
    0.91
     blame
    0.90
     speculate
    0.89
     easily
    0.88
    Activations Density 0.131%

    No Known Activations