© 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. 7-RES-JB
    11. 1520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sequence of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "Having," which implies a focus on past experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etter
    -0.64
     Echo
    -0.62
     Slovakia
    -0.61
    Interested
    -0.60
     Avalanche
    -0.58
    tel
    -0.57
     kicker
    -0.57
    etting
    -0.57
    ère
    -0.56
    VR
    -0.56
    POSITIVE LOGITS
     undergone
    1.18
     been
    1.14
     eaten
    0.97
     gotten
    0.93
     begun
    0.90
     seen
    0.90
     gone
    0.89
     arisen
    0.87
     learnt
    0.86
     tasted
    0.86
    Activations Density 0.031%

    No Known Activations