© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15693
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and comparisons in various fields

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to rankings and analysis in various contexts, particularly focusing on statistics and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ME
    -0.67
     Yugoslav
    -0.65
    atan
    -0.62
    ollah
    -0.61
    \)
    -0.61
    illus
    -0.60
    itialized
    -0.60
    eln
    -0.59
    plin
    -0.58
    actory
    -0.58
    POSITIVE LOGITS
     excellence
    0.91
     efficiency
    0.82
     prowess
    0.81
     innovation
    0.79
     firepower
    0.78
    anship
    0.77
     quality
    0.77
     sophistication
    0.76
     rankings
    0.76
     approvals
    0.75
    Activations Density 0.339%

    No Known Activations