© 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. 2-RES-JB
    11. 4463
    Prev
    Next
    INDEX
    Explanations

    words related to participles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to particle sizes and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Perkins
    -0.83
     Shack
    -0.79
    HCR
    -0.78
    ansas
    -0.74
     Leap
    -0.72
    DERR
    -0.69
    ahime
    -0.67
     Redemption
    -0.67
    xon
    -0.67
    finder
    -0.66
    POSITIVE LOGITS
    iple
    1.01
     partic
    0.91
    ulty
    0.84
    ulates
    0.83
    ã
    0.82
    resy
    0.82
    uations
    0.80
    ħ
    0.78
    ulum
    0.76
    ulate
    0.72
    Activations Density 0.015%

    No Known Activations