© 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. 17394
    Prev
    Next
    INDEX
    Explanations

    phrases related to famous quotes and sayings

    oai_token-act-pair · gpt-3.5-turbo

    well-known sayings or proverbs

    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
     è£ıè¦ļéĨĴ
    -0.72
    umably
    -0.69
    owicz
    -0.67
    catentry
    -0.66
    EA
    -0.66
     commented
    -0.65
    çīĪ
    -0.64
     Jian
    -0.63
    âĹ¼
    -0.62
     XD
    -0.61
    POSITIVE LOGITS
    Always
    0.98
     greatness
    0.96
     ALWAYS
    0.93
     shalt
    0.90
    cellence
    0.90
     Always
    0.89
     Thou
    0.88
    Never
    0.85
    thood
    0.84
     adversity
    0.83
    Activations Density 0.410%

    No Known Activations