© 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. 7-RES-JB
    11. 23639
    Prev
    Next
    INDEX
    Explanations

    Spanish words and phrases related to law and government

    oai_token-act-pair · gpt-3.5-turbo

    words related to administrative and governmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ply
    -0.88
    jri
    -0.85
    acle
    -0.80
    bler
    -0.78
    iley
    -0.77
    ndra
    -0.77
    fman
    -0.76
    enhagen
    -0.76
    pless
    -0.75
    illard
    -0.73
    POSITIVE LOGITS
     José
    0.85
     Nieto
    0.77
    ÃŃn
    0.75
    idad
    0.72
    ÃŃ
    0.72
     para
    0.71
    ional
    0.69
    ··
    0.67
     Luis
    0.67
    ón
    0.66
    Activations Density 0.028%

    No Known Activations