© 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. 1851
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity, particularly with the name "Amb"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or brand name associated with the term "Amb"

    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
    terday
    -0.76
    ãģ¦
    -0.75
    creen
    -0.74
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
     Ragnarok
    -0.71
    ãĥĩãĤ£
    -0.69
    ======
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    vous
    -0.67
    cloth
    -0.66
    POSITIVE LOGITS
    assadors
    1.20
    ient
    1.08
    assador
    1.06
    assad
    0.99
    iance
    0.93
    rose
    0.90
    ilar
    0.87
    iments
    0.86
    idy
    0.85
    ushes
    0.84
    Activations Density 0.006%

    No Known Activations