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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11336
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and establishments

    oai_token-act-pair · gpt-3.5-turbo

    references to political affiliations and social structures within communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acly
    -0.67
    ãĥ¼ãĥĨ
    -0.66
    ãĤ¶
    -0.62
    Bul
    -0.62
    Pg
    -0.60
    ãĤ¯
    -0.59
    ãĤ¦ãĤ¹
    -0.59
     Incre
    -0.59
    é¾įå
    -0.59
    ãĤ¤
    -0.57
    POSITIVE LOGITS
     rejoice
    0.99
     recognise
    0.88
     unite
    0.88
     agrees
    0.83
     dared
    0.78
     reacted
    0.77
     accuse
    0.76
     teamed
    0.76
     raided
    0.76
     allege
    0.75
    Activations Density 0.467%

    No Known Activations