© 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. 9-RES-JB
    11. 3619
    Prev
    Next
    INDEX
    Explanations

    information related to data analysis, research, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical data and patterns

    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
    eln
    -0.78
    cott
    -0.73
    udicrous
    -0.72
    çīĪ
    -0.70
    kit
    -0.66
    \\\\
    -0.65
    ©¶æ¥µ
    -0.64
    annon
    -0.64
    uti
    -0.64
    letes
    -0.62
    POSITIVE LOGITS
     trends
    1.27
     traject
    1.24
     indicators
    1.08
     characteristics
    1.06
     patterns
    1.06
     Trends
    1.04
     correlates
    1.02
     correlations
    0.99
     outcomes
    0.99
     responses
    0.97
    Activations Density 0.526%

    No Known Activations