© 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. 0-RES-JB
    11. 11281
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal actions and penal system

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sentence."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mount
    -0.83
    oots
    -0.80
    ounters
    -0.75
    oot
    -0.75
    alis
    -0.68
    Mount
    -0.68
    AppData
    -0.67
    rex
    -0.64
    mounted
    -0.62
     Indust
    -0.62
    POSITIVE LOGITS
     sentence
    3.80
     sentences
    3.00
    sent
    1.70
     sentencing
    1.64
     paragraph
    1.64
    paragraph
    1.42
     paragraphs
    1.41
     sentenced
    1.38
     phrase
    1.32
    Sent
    1.31
    Activations Density 0.023%

    No Known Activations