© 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
    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. 14178
    Prev
    Next
    INDEX
    Explanations

    mentions of legislative measures or programs

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legislative decisions and measures

    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
     Whilst
    -1.35
     whilst
    -1.26
    Picture
    -0.89
    Firstly
    -0.88
     Firstly
    -0.88
    â̦..
    -0.86
     !!
    -0.83
    â̦â̦â̦â̦
    -0.81
     apologise
    -0.80
     realise
    -0.80
    POSITIVE LOGITS
     afterward
    0.94
     nonprofits
    0.85
     nonprofit
    0.85
     aides
    0.82
     staffers
    0.80
     advisers
    0.75
     favored
    0.70
     nonpartisan
    0.70
     longtime
    0.69
     Whitman
    0.69
    Activations Density 1.534%

    No Known Activations