© 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. 3738
    Prev
    Next
    INDEX
    Explanations

    verbs related to decision-making and actions taken as a result

    oai_token-act-pair · gpt-3.5-turbo

    mentions of agreements or decisions related to political contexts

    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
     civilisation
    -0.77
     Whilst
    -0.72
     favourite
    -0.70
     flavours
    -0.69
    ?",
    -0.64
     ALWAYS
    -0.62
     HUGE
    -0.61
     NEVER
    -0.61
     Firstly
    -0.61
    usterity
    -0.61
    POSITIVE LOGITS
    .]
    1.00
    .[
    0.96
    .
    0.94
     thereto
    0.94
    .)
    0.94
     to
    0.93
    .''.
    0.90
    .�
    0.90
    .).
    0.89
     afterward
    0.87
    Activations Density 0.835%

    No Known Activations