© 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. 8-RES-JB
    11. 1257
    Prev
    Next
    INDEX
    Explanations

    keywords related to economic policies and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    financial terminology related to jobs, healthcare, and economic policies

    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
    trak
    -0.63
     condem
    -0.62
    Foot
    -0.62
    CLUD
    -0.61
    OLOG
    -0.60
     confir
    -0.57
    ":{"
    -0.56
    ULT
    -0.54
     PAN
    -0.53
    STRUCT
    -0.53
    POSITIVE LOGITS
     versus
    0.89
     whereas
    0.84
     whilst
    0.79
    ;}
    0.78
     contrasted
    0.77
     while
    0.76
    ?,
    0.76
     rather
    0.75
    })
    0.72
     ('
    0.72
    Activations Density 1.343%

    No Known Activations