© 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. 15020
    Prev
    Next
    INDEX
    Explanations

    sentence structures indicating the presence of information or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    references to changes and what is known or requires action

    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
    gart
    -0.77
    asers
    -0.69
    aser
    -0.66
     IDs
    -0.65
    chairs
    -0.60
     heels
    -0.59
     Outbreak
    -0.58
    upiter
    -0.57
    nels
    -0.57
    motion
    -0.57
    POSITIVE LOGITS
     done
    0.99
     accomplished
    0.94
     learnt
    0.88
     transpired
    0.87
     learned
    0.83
     glean
    0.83
     written
    0.82
     redacted
    0.80
    FINE
    0.78
     undone
    0.76
    Activations Density 0.149%

    No Known Activations