© 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. 8-RES-JB
    11. 6070
    Prev
    Next
    INDEX
    Explanations

    references to proper nouns or terms with special acronyms

    oai_token-act-pair · gpt-3.5-turbo

    words related to animal and plant species, particularly in a scientific or biological context

    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
     Subtle
    -0.88
     Darling
    -0.82
     Own
    -0.80
     Hurt
    -0.79
     Tracker
    -0.79
     Expend
    -0.78
     Accountability
    -0.78
     Breed
    -0.76
     Lack
    -0.75
     Yard
    -0.75
    POSITIVE LOGITS
    ouses
    0.89
    ensis
    0.88
    otype
    0.87
    ettes
    0.87
    omorph
    0.84
    iculture
    0.84
    oscopic
    0.83
    Äĵ
    0.83
    omial
    0.81
    ahs
    0.81
    Activations Density 0.281%

    No Known Activations