© 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. 7-RES-JB
    11. 8670
    Prev
    Next
    INDEX
    Explanations

    references to quality, emphasizing high quality or comparing quality to other attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quality assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coni
    -0.79
    opa
    -0.77
    cart
    -0.77
    ften
    -0.73
    usra
    -0.72
    kens
    -0.70
    oras
    -0.69
    stanbul
    -0.68
    mers
    -0.67
    apters
    -0.67
    POSITIVE LOGITS
     assurance
    1.41
     quality
    0.93
     improvement
    0.89
     measurement
    0.77
    Quality
    0.77
     equival
    0.76
     Quality
    0.74
     goods
    0.73
     retention
    0.72
     standards
    0.72
    Activations Density 0.028%

    No Known Activations