© 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. 8-RES-JB
    11. 23773
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "legitimate" across different contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legislation and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âķIJâķIJ
    -0.81
    KER
    -0.69
    terday
    -0.64
    ting
    -0.64
     kHz
    -0.62
    ter
    -0.62
    ãģį
    -0.61
    âĸ¬
    -0.60
    tery
    -0.60
    ¢
    -0.59
    POSITIVE LOGITS
    itimate
    1.38
    isl
    1.28
    acies
    1.17
    acy
    1.11
    enic
    1.02
    ends
    0.99
    rett
    0.98
    uin
    0.90
    edly
    0.86
    lav
    0.86
    Activations Density 0.030%

    No Known Activations