© 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. 7-RES-JB
    11. 12559
    Prev
    Next
    INDEX
    Explanations

    words related to forms of work or creation

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "do" and its related terms

    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
     srfAttach
    -0.70
     Defin
    -0.65
     Rivals
    -0.63
     Torment
    -0.63
     Pwr
    -0.61
    Ļ½
    -0.59
     substr
    -0.59
     WARRANT
    -0.58
    WARE
    -0.58
     hemor
    -0.58
    POSITIVE LOGITS
    imus
    0.79
    notation
    0.78
    aptic
    0.76
    ickey
    0.76
    ndra
    0.75
    ippi
    0.72
    sworth
    0.68
    rine
    0.68
    erous
    0.68
    mouth
    0.66
    Activations Density 0.095%

    No Known Activations