© 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. 2666
    Prev
    Next
    INDEX
    Explanations

    technical terms related to image processing and file manipulation

    oai_token-act-pair · gpt-3.5-turbo

    references to technical processes or components related to programming and digital media management

    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
     Huckabee
    -0.68
    onement
    -0.65
     Carney
    -0.65
    Conservative
    -0.65
    ortium
    -0.62
    galitarian
    -0.62
     Destroyer
    -0.62
    committee
    -0.62
    occup
    -0.62
    ucker
    -0.62
    POSITIVE LOGITS
     files
    1.41
     images
    1.37
     data
    1.36
     datasets
    1.34
     transcripts
    1.31
     sequences
    1.23
     messages
    1.22
     texts
    1.21
     documents
    1.20
     objects
    1.20
    Activations Density 0.415%

    No Known Activations