© 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. 132
    Prev
    Next
    INDEX
    Explanations

    comparative descriptions between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include comparative or relational phrases

    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
    wine
    -0.73
    Invalid
    -0.73
    DEN
    -0.70
    iband
    -0.69
    tun
    -0.68
    iverse
    -0.66
    dale
    -0.66
    breaker
    -0.65
    SourceFile
    -0.65
    Written
    -0.64
    POSITIVE LOGITS
     ours
    0.88
     other
    0.88
     peers
    0.87
     those
    0.81
     others
    0.81
     contemporaries
    0.80
     previous
    0.78
     what
    0.76
     comparable
    0.76
     usual
    0.74
    Activations Density 0.081%

    No Known Activations