© 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. 17581
    Prev
    Next
    INDEX
    Explanations

    references to the financial institution "Barclays" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the financial institution Barclays and associated entities or events

    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
    ning
    -0.77
    istically
    -0.75
    istic
    -0.74
    theless
    -0.69
    lessness
    -0.69
     Lomb
    -0.69
    less
    -0.67
    hood
    -0.67
    wright
    -0.66
    urses
    -0.66
    POSITIVE LOGITS
    hips
    1.42
    hip
    1.13
    erver
    1.09
    hell
    1.01
    ystem
    0.95
    hirt
    0.94
    heet
    0.92
    ocial
    0.92
    CRIP
    0.90
    chwitz
    0.88
    Activations Density 0.122%

    No Known Activations