© 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. 17632
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreeing to receive updates or offers

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consent and agreement

    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
    profits
    -0.75
    Champ
    -0.75
    killed
    -0.69
    hur
    -0.68
    hop
    -0.67
    abal
    -0.66
    âĢİ
    -0.65
    channelAvailability
    -0.65
    worth
    -0.64
    mania
    -0.62
    POSITIVE LOGITS
     abide
    0.72
     receive
    0.66
     participate
    0.64
     indemn
    0.64
     occasional
    0.61
     Terms
    0.61
     Participant
    0.61
     subscribe
    0.61
     waive
    0.60
     Privacy
    0.60
    Activations Density 0.026%

    No Known Activations