© 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. 4-RES-JB
    11. 452
    Prev
    Next
    INDEX
    Explanations

    phrases related to permission or authorization

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to permission or allowance

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

    No Comments

    Negative Logits
    ãĤ·ãĥ£
    -0.70
    ãĥ¯
    -0.69
    etheless
    -0.66
    é¾įå¥ij士
    -0.64
     Archdemon
    -0.62
     Stri
    -0.61
    quickShipAvailable
    -0.61
    æ©Ł
    -0.61
     Frequ
    -0.60
    luck
    -0.60
    POSITIVE LOGITS
     freely
    0.98
     safely
    0.88
     comfortably
    0.81
    ilaterally
    0.75
     unim
    0.75
     lawfully
    0.72
    rehend
    0.71
     unrestricted
    0.71
     disse
    0.70
     confidently
    0.70
    Activations Density 0.308%

    No Known Activations