© 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. 10-RES-JB
    11. 18532
    Prev
    Next
    INDEX
    Explanations

    specific occurrences of the word "the"

    oai_token-act-pair · gpt-3.5-turbo

    the start of a new text segment or paragraph

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ãĥ
    -0.60
     depending
    -0.58
    fare
    -0.58
     according
    -0.57
     [*
    -0.56
     accordingly
    -0.55
    —"
    -0.54
    according
    -0.52
    .*
    -0.51
    checks
    -0.51
    POSITIVE LOGITS
     Beginning
    0.66
     BOX
    0.64
     cellar
    0.63
     foreground
    0.62
     Philippines
    0.62
     Conversation
    0.61
     Forums
    0.61
     Discussion
    0.61
     Languages
    0.60
     nutshell
    0.60
    Activations Density 0.187%

    No Known Activations