© 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. 7-RES-JB
    11. 17246
    Prev
    Next
    INDEX
    Explanations

    texts following a pattern of special characters appearing in pairs in the middle of the text

    oai_token-act-pair · gpt-3.5-turbo

    topics related to various applications and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.86
    sing
    -0.69
    leigh
    -0.66
    tered
    -0.66
    dn
    -0.66
    lected
    -0.65
    boro
    -0.65
    acan
    -0.62
     HOU
    -0.61
    hest
    -0.60
    POSITIVE LOGITS
    ccording
    1.04
    ³³³³³³³³³³³³³³³³
    0.83
    ³³³³³³³³
    0.79
    ³³³
    0.69
     Similar
    0.67
     Prosecutors
    0.61
     Despite
    0.61
     Originally
    0.60
    ³³³³
    0.60
     Throughout
    0.60
    Activations Density 0.163%

    No Known Activations