© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12651
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions and decision making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions or policies involving inclusion, implications, or proposals

    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
    olitics
    -0.91
    ogyn
    -0.83
    Mine
    -0.80
    STAT
    -0.76
    ocene
    -0.74
    icter
    -0.71
    Appearance
    -0.70
    oiler
    -0.69
    abus
    -0.68
    ocry
    -0.68
    POSITIVE LOGITS
     replacing
    1.56
     installing
    1.56
     adopting
    1.55
     introducing
    1.55
     removing
    1.54
     abandoning
    1.51
     putting
    1.50
     appointing
    1.49
     eliminating
    1.49
     releasing
    1.48
    Activations Density 0.369%

    No Known Activations