© 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. 1-RES-JB
    11. 24242
    Prev
    Next
    INDEX
    Explanations

    words related to finding or discovery

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "finding."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mph
    -0.68
     paced
    -0.65
    perty
    -0.64
     Buff
    -0.63
    oiler
    -0.63
     concess
    -0.61
    pg
    -0.60
    roach
    -0.59
     Britann
    -0.59
     deb
    -0.59
    POSITIVE LOGITS
    Finding
    0.94
    -+-+
    0.88
    ãĤ¼
    0.87
    ãĤ¤ãĥĪ
    0.86
    finding
    0.86
    ãĤ¦ãĤ¹
    0.86
    Ô
    0.83
    ually
    0.82
    ä¸ī
    0.81
    ãĤ¼ãĤ¦ãĤ¹
    0.75
    Activations Density 0.008%

    No Known Activations