© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18656
    Prev
    Next
    INDEX
    Explanations

    dollar amounts mentioned in text, particularly in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    financial contributions related to political campaigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ageing
    -0.94
    }}}
    -0.84
    terness
    -0.81
     deterior
    -0.72
     solved
    -0.70
    uku
    -0.69
     strugg
    -0.68
     pests
    -0.67
     madness
    -0.67
     2050
    -0.66
    POSITIVE LOGITS
     donations
    1.15
     donated
    1.09
    clinton
    1.08
     donation
    1.04
     PACs
    1.03
     contributions
    1.01
     gifts
    1.00
     reimburse
    1.00
    esta
    0.99
     fundra
    0.99
    Activations Density 0.227%

    No Known Activations