© 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. 10-RES-JB
    11. 24032
    Prev
    Next
    INDEX
    Explanations

    phrases related to IDs, licenses, permits, and credentials

    oai_token-act-pair · gpt-3.5-turbo

    references to identification and credentials requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    players
    -0.78
    "]=>
    -0.75
     pandemonium
    -0.73
    scenes
    -0.73
    Players
    -0.72
    storms
    -0.71
    optim
    -0.71
    NetMessage
    -0.70
     Despair
    -0.69
    oops
    -0.68
    POSITIVE LOGITS
     authorization
    1.50
     license
    1.43
     licenses
    1.40
     passport
    1.37
     licence
    1.36
     permit
    1.36
     licences
    1.35
     registration
    1.34
     permits
    1.33
     passports
    1.31
    Activations Density 0.363%

    No Known Activations