© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18695
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to specific actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and requirements related to projects or processes

    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
    lez
    -0.73
    ussia
    -0.73
    trak
    -0.73
     Hatt
    -0.70
    hesda
    -0.68
    okane
    -0.65
    ommel
    -0.65
    hander
    -0.64
    nant
    -0.64
    pheus
    -0.63
    POSITIVE LOGITS
     Secondly
    1.05
     secondly
    0.98
    %;
    0.79
    Secondly
    0.78
     //[
    0.74
    ³³³³
    0.74
     Whereas
    0.73
     Currently
    0.72
     Specifically
    0.72
     Additionally
    0.71
    Activations Density 0.454%

    No Known Activations