© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13355
    Prev
    Next
    INDEX
    Explanations

    phrases related to keeping or maintaining something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to maintaining or keeping something intact

    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
    ode
    -0.74
    FORE
    -0.69
    gom
    -0.63
    ULE
    -0.62
    Sys
    -0.62
    PsyNetMessage
    -0.62
    WARNING
    -0.61
    ologue
    -0.61
    Ja
    -0.61
    Gs
    -0.60
    POSITIVE LOGITS
     intact
    0.88
     memories
    0.80
     tabs
    0.77
     composure
    0.77
     retained
    0.75
     possession
    0.74
     ownership
    0.74
     momentum
    0.73
     liberties
    0.73
     custody
    0.72
    Activations Density 0.030%

    No Known Activations