© 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. 20629
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    details related to electronic device components and their connections

    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
    Percent
    -0.96
    Ô
    -0.96
    votes
    -0.86
    soType
    -0.84
    writ
    -0.82
    Attempts
    -0.76
    racial
    -0.75
    aclysm
    -0.75
    onyms
    -0.73
    staking
    -0.73
    POSITIVE LOGITS
     chassis
    1.34
     underside
    1.28
     receiver
    1.19
     motherboard
    1.16
     rear
    1.15
     headset
    1.13
     enclosure
    1.09
     unit
    1.08
     casing
    1.07
     transmitter
    1.06
    Activations Density 0.174%

    No Known Activations