© 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. 9953
    Prev
    Next
    INDEX
    Explanations

    action prompts related to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    prepositions or phrases indicating action or direction

    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
    anooga
    -0.62
    terday
    -0.61
    ersive
    -0.58
    iddles
    -0.58
    nces
    -0.57
    çľ
    -0.56
     passers
    -0.54
     dwar
    -0.54
    hai
    -0.53
    ccording
    -0.51
    POSITIVE LOGITS
     subscribe
    1.12
     Subscribe
    0.78
    register
    0.75
    pload
    0.71
    Subscribe
    0.67
     refresh
    0.67
     subscribing
    0.66
     unsub
    0.65
     subscribed
    0.65
    erk
    0.64
    Activations Density 0.020%

    No Known Activations