© 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. 1-RES-JB
    11. 3780
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people or places, combined with some additional text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "lost" and related lexical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icester
    -0.75
    asuring
    -0.72
    hm
    -0.72
    lahoma
    -0.69
    dem
    -0.66
    gers
    -0.64
    auga
    -0.64
     Dug
    -0.64
    acity
    -0.62
     Schne
    -0.62
    POSITIVE LOGITS
    LY
    1.26
    STON
    1.19
    OST
    1.16
    ULAR
    1.15
    IAL
    1.13
    URN
    1.13
    NESS
    1.12
    UR
    1.11
    ESH
    1.10
    AGE
    1.10
    Activations Density 0.022%

    No Known Activations