© 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. 11-RES-JB
    11. 400
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions taken by individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    the verb "has" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    has/have after but, despite, although, etc.

    Explanation Uploaded by User
    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
     Recre
    -0.69
    tackle
    -0.66
    ribute
    -0.66
    eem
    -0.64
    hand
    -0.61
     Supports
    -0.61
    auer
    -0.59
    mast
    -0.59
    rolling
    -0.59
    isbury
    -0.59
    POSITIVE LOGITS
     struggled
    1.19
     yet
    1.17
     lacked
    1.12
     begun
    1.08
     opted
    1.03
     failed
    1.00
     resisted
    0.99
     been
    0.99
     dodged
    0.98
     remained
    0.96
    Activations Density 0.256%

    No Known Activations