© 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. 6842
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to allowing actions

    oai_token-act-pair · gpt-3.5-turbo

    references to subjects and their permissions or capabilities

    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
    ruck
    -0.53
    erno
    -0.53
    pak
    -0.52
    raid
    -0.52
    ilings
    -0.51
    requires
    -0.50
    uesday
    -0.49
    doi
    -0.49
    arling
    -0.49
    consumer
    -0.49
    POSITIVE LOGITS
     access
    0.96
     flexibility
    0.95
     unlimited
    0.94
     to
    0.93
     unrestricted
    0.89
     ample
    0.83
     limitless
    0.77
     freedom
    0.77
     anonymity
    0.71
     freely
    0.69
    Activations Density 0.120%

    No Known Activations