Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22819
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a beginning or initial stage of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the concept of beginnings or initial stages

    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
    thood
    -0.75
    imar
    -0.70
    lan
    -0.68
    ibo
    -0.68
    awaru
    -0.66
    abel
    -0.65
    amsung
    -0.65
    aways
    -0.64
    AMA
    -0.64
    chwitz
    -0.63
    POSITIVE LOGITS
     tip
    1.32
     beginning
    1.20
     slightest
    1.08
     Beginning
    1.03
     latest
    1.03
     icing
    0.96
     beginnings
    0.93
     appet
    0.90
     Facts
    0.87
     start
    0.83
    Activations Density 0.051%

    No Known Activations