© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1371
    Prev
    Next
    INDEX
    Explanations

    the word "here" used in a context of presence or intention

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the reasons or motivations behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.66
    éŃĶ
    -0.62
    acia
    -0.60
    pton
    -0.60
    nce
    -0.59
    webkit
    -0.57
    ··
    -0.57
    orse
    -0.57
     THREE
    -0.55
    True
    -0.55
    POSITIVE LOGITS
     recreational
    0.99
     entertainment
    0.99
     novelty
    0.98
     convenience
    0.96
     informational
    0.96
     amusement
    0.95
     hobby
    0.93
     curiosity
    0.90
     decorative
    0.89
     amuse
    0.87
    Activations Density 0.507%

    No Known Activations