© 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. 3-RES-JB
    11. 21167
    Prev
    Next
    INDEX
    Explanations

    references or mentions of the British

    oai_token-act-pair · gpt-3.5-turbo

    references to British entities or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -1.07
    apego
    -0.89
    pty
    -0.83
    oldemort
    -0.83
    anwhile
    -0.83
    tp
    -0.80
    afort
    -0.79
    ologies
    -0.78
    icago
    -0.77
    ktop
    -0.77
    POSITIVE LOGITS
     Isles
    1.25
     Columbia
    1.21
     Columb
    1.10
     Airways
    1.08
     Union
    0.91
     Forces
    0.89
     Crown
    0.88
     Virgin
    0.86
     Broadcasting
    0.85
     Steel
    0.83
    Activations Density 0.015%

    No Known Activations