© 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. 1-RES-JB
    11. 3894
    Prev
    Next
    INDEX
    Explanations

    words related to receiving and obtaining information or objects that are already prepared or available

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "got."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depiction
    -0.70
    SPONSORED
    -0.67
    oin
    -0.66
    ilings
    -0.63
    illusion
    -0.63
     Archdemon
    -0.62
    cair
    -0.62
    arta
    -0.62
    Ale
    -0.61
    livious
    -0.60
    POSITIVE LOGITS
     rid
    0.98
    ãĥ³ãĤ¸
    0.79
    wb
    0.78
     bog
    0.77
     nab
    0.75
    hers
    0.73
     precedence
    0.73
    terson
    0.71
     into
    0.71
    TING
    0.70
    Activations Density 0.030%

    No Known Activations