© 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. 11-RES-JB
    11. 9343
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and political terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotions or conflicts

    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
     âĢ¦"
    -1.03
     ÂŃ
    -0.98
     âĢ¦
    -0.95
     [âĢ¦]
    -0.89
    âĢ¦."
    -0.87
     âĪ¼
    -0.81
     undermin
    -0.75
    SPONSORED
    -0.75
     ninety
    -0.74
    ÂŃ
    -0.73
    POSITIVE LOGITS
    )-
    1.45
     -
    1.35
    .-
    1.17
    :-
    1.16
    ↵↵
    1.11
     "-
    1.00
    -)
    1.00
    -(
    0.99
    '-
    0.96
    --------------------------------------------------------
    0.92
    Activations Density 0.146%

    No Known Activations