© 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. 2718
    Prev
    Next
    INDEX
    Explanations

    phrases related to cleanliness and purity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating purity or the absence of undesirable substances

    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
     successfully
    -0.79
    isSpecialOrderable
    -0.76
    20439
    -0.75
     Alive
    -0.75
     Enabled
    -0.75
     reinstated
    -0.73
     YES
    -0.72
    ESE
    -0.71
    ttp
    -0.71
     Excellent
    -0.71
    POSITIVE LOGITS
     fuss
    1.10
     intrusive
    0.99
     coercion
    0.97
     distractions
    0.96
     prejudice
    0.95
     distortion
    0.94
     gimm
    0.94
     wasteful
    0.93
     compromises
    0.93
     interference
    0.93
    Activations Density 0.347%

    No Known Activations