© 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. 11-RES-JB
    11. 18576
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong actions or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social and moral issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oaks
    -0.63
     Gideon
    -0.63
    200000
    -0.61
     Robbie
    -0.60
    iage
    -0.58
     LH
    -0.58
    ilan
    -0.57
    ertility
    -0.56
     Kro
    -0.56
     Liberty
    -0.55
    POSITIVE LOGITS
    »
    2.00
    âĢ
    1.84
    ''
    1.79
     âĢ
    1.68
    ãĢį
    1.67
    ãĢ
    1.61
    ''.
    1.55
    [/
    1.53
    ¨
    1.47
    </
    1.46
    Activations Density 0.688%

    No Known Activations