© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 1480
    Prev
    Next
    INDEX
    Explanations

    prefixes "-anti" followed by words related to various societal issues or activism

    oai_token-act-pair · gpt-3.5-turbo

    references to anti-establishment or anti-government sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.78
    swick
    -0.73
     Brist
    -0.72
     WD
    -0.70
    ulhu
    -0.70
    çīĪ
    -0.70
     Cohn
    -0.67
     ILCS
    -0.67
     Nieto
    -0.66
     leaps
    -0.65
    POSITIVE LOGITS
    establishment
    1.28
    social
    1.19
    government
    1.17
    Semitic
    1.16
    competitive
    1.10
    commun
    1.06
    gravity
    1.03
    capitalist
    1.02
    democratic
    1.02
    Semitism
    1.00
    Activations Density 0.030%

    No Known Activations