© 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. 9881
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the start or initiation of an action or process

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "begin" and its variations

    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
    allo
    -0.77
    =-=-=-=-=-=-=-=-
    -0.69
    ndra
    -0.65
    dad
    -0.65
    leneck
    -0.61
     Away
    -0.61
    eteria
    -0.61
    eros
    -0.61
     IMAGES
    -0.60
     Heard
    -0.60
    POSITIVE LOGITS
     anew
    1.01
     circulating
    0.81
     withdrawing
    0.80
     plotting
    0.79
     cultivating
    0.78
     assembling
    0.77
     dismantling
    0.77
     experimenting
    0.76
     preparations
    0.76
    ŃĶ
    0.76
    Activations Density 0.051%

    No Known Activations