© 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. 7-RES-JB
    11. 13372
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate starting a narrative or discussion

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "start with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    span
    -0.73
    hops
    -0.71
    agues
    -0.69
     span
    -0.67
    supported
    -0.65
    late
    -0.64
    affected
    -0.62
    stre
    -0.61
    wik
    -0.61
    paced
    -0.60
    POSITIVE LOGITS
     respect
    0.78
     obvious
    0.73
    draw
    0.72
     regard
    0.70
    amaz
    0.68
     regards
    0.67
     basics
    0.65
     introdu
    0.64
     apologies
    0.64
     Rowe
    0.63
    Activations Density 0.040%

    No Known Activations