© 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. 24304
    Prev
    Next
    INDEX
    Explanations

    financial terms or phrases related to business and economic activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting elements in the text

    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
    etheless
    -0.77
     undermin
    -0.69
     Pompe
    -0.67
    lyak
    -0.66
    aeda
    -0.66
    odox
    -0.62
    20439
    -0.62
    Newsletter
    -0.60
     Giul
    -0.59
    weights
    -0.59
    POSITIVE LOGITS
     CBC
    0.92
    CBC
    0.90
     Winnipeg
    0.79
     RCMP
    0.71
     councillor
    0.71
     Manitoba
    0.70
     CFL
    0.69
     Scotia
    0.69
     Halifax
    0.68
     Edmonton
    0.68
    Activations Density 0.141%

    No Known Activations