© 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. 7-RES-JB
    11. 23403
    Prev
    Next
    INDEX
    Explanations

    covert instructions or hidden terms within messages

    oai_token-act-pair · gpt-3.5-turbo

    criteria for eligibility in competitions or promotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.68
    razen
    -0.67
     disadvant
    -0.63
     overshadow
    -0.62
     undermin
    -0.61
    ãĥ³ãĤ¸
    -0.59
    pher
    -0.58
    Ò
    -0.58
     behavi
    -0.57
    ppard
    -0.57
    POSITIVE LOGITS
     Cancel
    0.88
     Submit
    0.83
     Login
    0.79
     Shipping
    0.77
     ORDER
    0.77
     Refresh
    0.75
     Payment
    0.74
     Purchase
    0.74
     Apply
    0.74
     Username
    0.74
    Activations Density 0.806%

    No Known Activations