© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 2471
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or initiation of a process or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "started."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obi
    -0.81
    âĨij
    -0.76
     entirety
    -0.67
    omb
    -0.67
    ugs
    -0.66
    warts
    -0.64
    cit
    -0.63
    airy
    -0.63
    cedented
    -0.63
    cation
    -0.62
    POSITIVE LOGITS
     anew
    1.12
     noticing
    0.92
     experimenting
    0.89
     behaving
    0.84
     bothering
    0.82
     researching
    0.82
     accumulating
    0.80
     dating
    0.80
     acting
    0.76
     deleting
    0.75
    Activations Density 0.068%

    No Known Activations