© 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. 11335
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change of topic or a new statement within a discussion

    oai_token-act-pair · gpt-3.5-turbo

    transitional phrases and expressions indicating uncertainty or opinions

    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
    iership
    -0.65
    oided
    -0.64
     Wellington
    -0.59
     recognised
    -0.58
     woodland
    -0.55
     torpedo
    -0.53
     honoured
    -0.52
     favoured
    -0.52
     ejected
    -0.52
     foil
    -0.51
    POSITIVE LOGITS
    âĢ
    1.93
    [/
    1.45
     âĢ
    1.44
    ãĢ
    1.42
    </
    1.41
    >>>>
    1.39
    âĺ
    1.38
    âĶ
    1.33
    »
    1.32
    âľ
    1.29
    Activations Density 0.899%

    No Known Activations