© 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. 20404
    Prev
    Next
    INDEX
    Explanations

    phrases related to independence and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to independent entities and investigations

    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
    Spread
    -0.97
    rame
    -0.73
    rises
    -0.72
    anguages
    -0.71
     slogans
    -0.70
    ocations
    -0.69
    BOOK
    -0.68
     selfies
    -0.68
    opsis
    -0.68
    SourceFile
    -0.66
    POSITIVE LOGITS
     tribunal
    1.41
     investigator
    1.39
     inspectors
    1.37
     panel
    1.36
     committee
    1.35
     investigators
    1.33
     jury
    1.33
     experts
    1.31
     impartial
    1.31
     inspector
    1.31
    Activations Density 0.393%

    No Known Activations