© 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. 9-RES-JB
    11. 9848
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software or product features

    oai_token-act-pair · gpt-3.5-turbo

    mentions of features and updates related to technology or software releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accuses
    -0.78
    rique
    -0.65
    erity
    -0.64
     accusing
    -0.63
     blames
    -0.63
     reckoning
    -0.63
     blaming
    -0.62
     Buchanan
    -0.61
     Crane
    -0.60
     Fairfax
    -0.60
    POSITIVE LOGITS
     included
    0.91
    mentioned
    0.89
     incorporated
    0.89
     Included
    0.85
     additions
    0.82
    Introduced
    0.82
     added
    0.81
     implemented
    0.81
     unlocked
    0.81
     applicable
    0.80
    Activations Density 0.583%

    No Known Activations