© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18618
    Prev
    Next
    INDEX
    Explanations

    phrases indicating understanding or comprehension

    oai_token-act-pair · gpt-3.5-turbo

    expressions of understanding or empathy

    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
    âĢ
    -0.97
    âĢİ
    -0.86
    à¨
    -0.83
    à©
    -0.83
    æł
    -0.81
    ãĤ£
    -0.79
    è»
    -0.79
     âĢ
    -0.79
    etheus
    -0.76
     à¨
    -0.76
    POSITIVE LOGITS
     ;)
    1.12
     haha
    1.05
     :)
    1.03
    !?
    1.02
     :(
    1.01
    ?!
    1.01
    !
    0.99
    ...?
    0.91
     dude
    0.90
     anyways
    0.90
    Activations Density 0.701%

    No Known Activations