© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 19058
    Prev
    Next
    INDEX
    Explanations

    sentences or fragments that convey factual information or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentences or phrases that describe the outcome or result of a particular action or situation

    oai_token-act-pair · gpt-3.5-turbo
    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
     purse
    -0.68
    leep
    -0.64
     couch
    -0.63
     sed
    -0.63
     recl
    -0.63
     stale
    -0.62
     tempt
    -0.61
     challeng
    -0.61
     slightest
    -0.61
     nodd
    -0.60
    POSITIVE LOGITS
     Additionally
    0.94
     Also
    0.91
     Similarly
    0.90
     Later
    0.86
     However
    0.86
     According
    0.86
     Meanwhile
    0.84
     Unfortunately
    0.83
     Along
    0.81
     Furthermore
    0.81
    Activations Density 0.769%

    No Known Activations