© 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. 4753
    Prev
    Next
    INDEX
    Explanations

    phrases containing instructions or notes

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that provide clarifications or additional context

    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
    acerb
    -0.74
    ONSORED
    -0.72
    polit
    -0.69
     presided
    -0.68
    ridor
    -0.68
     earnest
    -0.67
    USS
    -0.67
    âĢİ
    -0.67
     disillusion
    -0.67
    egal
    -0.67
    POSITIVE LOGITS
     you
    0.99
     if
    0.94
     whenever
    0.92
     depending
    0.92
     Users
    0.90
     Suppose
    0.90
     disabling
    0.89
     lets
    0.89
     storing
    0.89
    allows
    0.89
    Activations Density 0.428%

    No Known Activations