© 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. 7081
    Prev
    Next
    INDEX
    Explanations

    email invitations to share or send something to a friend

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve sending or sharing information

    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
    andowski
    -0.72
    ADVERTISEMENT
    -0.65
    verage
    -0.65
    åº
    -0.63
    osure
    -0.62
     Coverage
    -0.61
    cipline
    -0.60
    ###
    -0.59
    cipl
    -0.59
    Tickets
    -0.58
    POSITIVE LOGITS
     yourself
    0.87
    entin
    0.77
     myself
    0.77
     ourselves
    0.74
    washer
    0.74
     whoever
    0.70
    unes
    0.70
     oneself
    0.69
    Ħ¢
    0.67
    alone
    0.66
    Activations Density 0.272%

    No Known Activations