© 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. 10-RES-JB
    11. 2657
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions or treatments, particularly focusing on the prefix "trop" with varying degrees of intensity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tropical or subtropical environments and their ecological factors

    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
     awoken
    -0.62
     intent
    -0.62
     CTR
    -0.62
     diligence
    -0.60
    è£
    -0.60
    mates
    -0.60
     resemblance
    -0.59
    Page
    -0.59
     captcha
    -0.58
     Blair
    -0.57
    POSITIVE LOGITS
    oulos
    1.36
    hedon
    1.21
    olitics
    1.06
    ython
    1.04
    onte
    1.02
    ower
    1.01
    tera
    0.99
    ract
    0.97
    hens
    0.95
    onent
    0.95
    Activations Density 0.030%

    No Known Activations