© 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. 11-RES-JB
    11. 21772
    Prev
    Next
    INDEX
    Explanations

    phrases related to making changes or modifications

    oai_token-act-pair · gpt-3.5-turbo

    references to changes in systems, processes, or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.67
    solid
    -0.65
    ymph
    -0.63
    GV
    -0.61
    culosis
    -0.59
    >)
    -0.58
    unts
    -0.57
    aband
    -0.57
     laughs
    -0.57
     Bei
    -0.55
    POSITIVE LOGITS
     accordingly
    1.32
     drastically
    1.27
     dramatically
    1.13
     radically
    1.13
     substantially
    0.91
     fundamentally
    0.91
     subtly
    0.87
     abruptly
    0.85
     significantly
    0.84
     unilaterally
    0.84
    Activations Density 0.320%

    No Known Activations