© 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. 4-RES-JB
    11. 24149
    Prev
    Next
    INDEX
    Explanations

    words related to newness or beginning stages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the early stages of development or growth

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

    No Comments

    Negative Logits
    gio
    -0.73
    idon
    -0.66
    ably
    -0.65
    ricanes
    -0.64
    oho
    -0.63
    zzi
    -0.62
     cited
    -0.61
    phe
    -0.61
     evacuate
    -0.61
    gged
    -0.61
    POSITIVE LOGITS
     budding
    0.86
    escent
    0.77
    cape
    0.77
    lings
    0.76
     entreprene
    0.76
     fledgling
    0.73
    reprene
    0.66
     entrepreneurial
    0.65
    ocument
    0.65
     anew
    0.65
    Activations Density 0.028%

    No Known Activations