© 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. 22336
    Prev
    Next
    INDEX
    Explanations

    abbreviated phrases such as "Vis TA" or "Insp ir."

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic or creative projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     afterward
    -0.69
     respectively
    -0.67
     thereto
    -0.65
    )."
    -0.64
     downstream
    -0.61
    ]."
    -0.61
     anymore
    -0.60
     beforehand
    -0.60
     therein
    -0.59
    âĢ¦."
    -0.59
    POSITIVE LOGITS
     âĵĺ
    0.97
    tymology
    0.89
     Profile
    0.88
    ibliography
    0.88
    !:
    0.86
    iquette
    0.83
    udos
    0.79
    itars
    0.78
    isode
    0.77
    ':
    0.77
    Activations Density 0.764%

    No Known Activations