© 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. 7603
    Prev
    Next
    INDEX
    Explanations

    formal or official occurrences or declarations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate formal declarations or statuses

    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
    ĸļ
    -0.74
     disproportion
    -0.73
    ngth
    -0.70
     realistically
    -0.69
    igent
    -0.67
     curiously
    -0.67
    ĺħ
    -0.67
     carefully
    -0.66
     mainly
    -0.65
    =-=-=-=-=-=-=-=-
    -0.65
    POSITIVE LOGITS
     sanctioned
    1.16
     endorsed
    1.00
     declared
    0.94
     disbanded
    0.93
     recognised
    0.91
     acknowledged
    0.90
     ratified
    0.90
     recognized
    0.89
     announced
    0.89
     retired
    0.87
    Activations Density 0.042%

    No Known Activations