© 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. 13455
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to opinions or assessments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "it’s" or similar contractions and the contexts they are used in

    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
     stumbling
    -0.69
     boarding
    -0.67
     stuffing
    -0.67
     juggling
    -0.66
     sleeping
    -0.66
     Skydragon
    -0.65
     scattering
    -0.65
     dumping
    -0.65
     forwarding
    -0.64
     rotating
    -0.64
    POSITIVE LOGITS
    should
    0.93
    felt
    0.92
    Pg
    0.92
    uates
    0.92
    udes
    0.89
    ould
    0.88
    ï¸ı
    0.86
    won
    0.85
    dri
    0.84
     beh
    0.84
    Activations Density 0.196%

    No Known Activations