© 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. 8-RES-JB
    11. 2470
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the acquisition of new information or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the acquisition of knowledge or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç¥ŀ
    -0.76
    ãĥª
    -0.68
    ciating
    -0.66
    uked
    -0.65
    bec
    -0.64
    wake
    -0.64
    comes
    -0.63
    à
    -0.63
    ende
    -0.63
    iru
    -0.63
    POSITIVE LOGITS
     anecd
    0.90
     Sources
    0.80
     Fairfax
    0.74
     firsthand
    0.69
     indications
    0.69
     Hancock
    0.68
     eyewitness
    0.68
     informant
    0.67
     neither
    0.65
     sources
    0.65
    Activations Density 0.174%

    No Known Activations