© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 14087
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are alike or resemble one another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "similar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arden
    -0.77
    arest
    -0.75
    hest
    -0.72
    hend
    -0.71
    OST
    -0.69
    Diamond
    -0.68
    ensibly
    -0.66
    Benz
    -0.66
    gemony
    -0.65
    ellen
    -0.65
    POSITIVE LOGITS
     sized
    1.17
     sentiments
    1.13
     minded
    1.06
     fate
    1.05
    lihood
    1.04
     vein
    1.03
     phenomena
    1.01
    ities
    0.99
    worldly
    0.97
     phenomenon
    0.95
    Activations Density 0.035%

    No Known Activations