© 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. 8-RES-JB
    11. 6180
    Prev
    Next
    INDEX
    Explanations

    keywords related to political donations and financial contributions

    oai_token-act-pair · gpt-3.5-turbo

    references to financial contributions and donations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }}}
    -0.92
    obyl
    -0.92
    terness
    -0.85
    ĸļ
    -0.84
     ageing
    -0.83
     solved
    -0.79
    士
    -0.77
     Classification
    -0.77
     ILCS
    -0.76
    hani
    -0.76
    POSITIVE LOGITS
     fundra
    1.28
     donated
    1.27
     fundraising
    1.24
     PACs
    1.24
     donations
    1.21
     donors
    1.18
     charitable
    1.16
     Podesta
    1.15
     donor
    1.12
     donating
    1.11
    Activations Density 0.598%

    No Known Activations