© 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. 9-RES-JB
    11. 7367
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting something inevitable or unable to be avoided

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases that denote necessity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erva
    -0.95
    ffield
    -0.87
    anooga
    -0.87
    imore
    -0.86
    emis
    -0.85
    ivas
    -0.83
    ington
    -0.83
    ickr
    -0.82
    anchester
    -0.80
    vertisement
    -0.80
    POSITIVE LOGITS
     doom
    0.86
     truths
    0.73
     srfAttach
    0.72
     Danger
    0.69
     consequences
    0.69
     Cruel
    0.69
     pandemonium
    0.67
     defeat
    0.67
     conclud
    0.67
     consequence
    0.67
    Activations Density 0.127%

    No Known Activations