© 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. 3532
    Prev
    Next
    INDEX
    Explanations

    words related to political discussions and opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases or mentions that convey uncertainty or questioning about a situation

    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
     Tanz
    -0.74
     captives
    -0.71
    geries
    -0.69
     sacrific
    -0.66
     mathemat
    -0.65
     filib
    -0.65
     Palestin
    -0.65
     hostages
    -0.63
     princ
    -0.60
    ITNESS
    -0.60
    POSITIVE LOGITS
    ï¸ı
    0.82
    ï¸
    0.77
    Pg
    0.76
    uable
    0.75
    eal
    0.73
    else
    0.72
    should
    0.71
     deserves
    0.69
    mir
    0.69
    forth
    0.69
    Activations Density 0.242%

    No Known Activations