© 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. 2-RES-JB
    11. 21249
    Prev
    Next
    INDEX
    Explanations

    terms related to physical discomfort or medical conditions involving muscle cramping

    oai_token-act-pair · gpt-3.5-turbo

    words related to critical elements or reasoning, particularly around the use of "cr" terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -0.87
    eers
    -0.83
    DragonMagazine
    -0.80
    é¾įå
    -0.76
    EMENT
    -0.75
    IELD
    -0.74
     Dragonbound
    -0.74
    geist
    -0.74
     Masters
    -0.73
     Hunters
    -0.73
    POSITIVE LOGITS
    umb
    1.15
    umbled
    1.03
    umbs
    0.98
    umin
    0.92
    anked
    0.90
    anium
    0.87
    udge
    0.87
    umbles
    0.86
    amping
    0.85
    udging
    0.85
    Activations Density 0.006%

    No Known Activations