© 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. 8-RES-JB
    11. 18624
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating a source or origin

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating demands or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idi
    -0.77
    itialized
    -0.72
    acet
    -0.71
    irm
    -0.71
    flix
    -0.71
    motion
    -0.71
    je
    -0.71
    iken
    -0.69
    unes
    -0.69
    puter
    -0.68
    POSITIVE LOGITS
     afar
    1.39
     abroad
    0.91
     whence
    0.86
     inside
    0.85
     us
    0.85
     anywhere
    0.85
     anyone
    0.83
     him
    0.82
     anybody
    0.80
     within
    0.77
    Activations Density 0.105%

    No Known Activations