© 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. 0-RES-JB
    11. 2424
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to image resolution in electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to multimedia protocols or technology related to media processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atlantis
    -0.70
     sage
    -0.68
     derby
    -0.67
     fulfillment
    -0.67
     consolation
    -0.67
     Aristotle
    -0.66
     Cherokee
    -0.65
     intim
    -0.65
     bowl
    -0.65
     prevail
    -0.64
    POSITIVE LOGITS
    MP
    4.33
    mp
    2.01
     MP
    1.96
    Mp
    1.58
    PP
    1.52
    LP
    1.50
     mp
    1.49
    MK
    1.41
    CP
    1.34
    HK
    1.34
    Activations Density 0.007%

    No Known Activations