© 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. 10-RES-JB
    11. 16198
    Prev
    Next
    INDEX
    Explanations

    technology-related terms or phrases, particularly related to information technology and innovation

    oai_token-act-pair · gpt-3.5-turbo

    elements related to straightforward solutions or innovative strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Secondly
    -0.75
     Also
    -0.74
     alot
    -0.68
     secondly
    -0.68
    Secondly
    -0.66
     independ
    -0.65
     SUPPORT
    -0.64
     ALSO
    -0.63
     Relations
    -0.63
    Regarding
    -0.62
    POSITIVE LOGITS
     whiff
    0.78
     uttered
    0.78
     glance
    0.76
     stroll
    0.74
     innocuous
    0.72
     fingert
    0.71
     tucked
    0.71
     millisec
    0.70
     blinking
    0.68
     ticking
    0.68
    Activations Density 1.051%

    No Known Activations