© 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. 11-RES-JB
    11. 4148
    Prev
    Next
    INDEX
    Explanations

    numerical specifications or features of electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    numeric specifications related to electronic devices

    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
     Annotations
    -0.66
     Cutter
    -0.65
     Leilan
    -0.62
    naire
    -0.62
    naires
    -0.59
     Pupp
    -0.59
    orc
    -0.56
     closing
    -0.56
     McN
    -0.54
     flatt
    -0.54
    POSITIVE LOGITS
    GB
    1.30
    TB
    1.20
    GHz
    1.19
    Gb
    1.16
    MP
    1.12
    Mbps
    1.04
     GB
    0.97
    gb
    0.97
    MB
    0.94
    Mp
    0.93
    Activations Density 0.063%

    No Known Activations