© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18496
    Prev
    Next
    INDEX
    Explanations

    expressions related to freedom or permission

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate permission or freedom of action

    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
     millenn
    -0.77
    quickShipAvailable
    -0.72
    ¿½
    -0.72
    bush
    -0.68
    UF
    -0.68
    ELD
    -0.67
    need
    -0.65
    IJ
    -0.64
    hur
    -0.64
    fee
    -0.62
    POSITIVE LOGITS
     roam
    1.15
     explore
    1.13
     choose
    1.07
     indulge
    1.04
     ignore
    0.99
     pursue
    0.99
     speculate
    0.94
     criticize
    0.93
     participate
    0.93
     improv
    0.90
    Activations Density 0.126%

    No Known Activations