© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21248
    Prev
    Next
    INDEX
    Explanations

    the word "Sad" or numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to characters named "Sad" and numerical values

    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
    姫
    -0.79
     Lauder
    -0.77
    YING
    -0.71
    matically
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.69
    ARD
    -0.69
    MW
    -0.68
    IVER
    -0.67
    pool
    -0.67
     Aware
    -0.67
    POSITIVE LOGITS
    emic
    0.92
    erences
    0.91
    eral
    0.82
    iso
    0.80
    eway
    0.79
    ocaly
    0.77
    uro
    0.76
    erer
    0.76
    emia
    0.76
    etr
    0.75
    Activations Density 0.054%

    No Known Activations