© 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
    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. 2746
    Prev
    Next
    INDEX
    Explanations

    terms related to technical services and management in various industries

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and related phrases indicating connections or relationships between concepts

    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
    pees
    -1.04
    kees
    -0.98
    wic
    -0.89
    ieth
    -0.86
    aws
    -0.84
    viks
    -0.82
    Laughs
    -0.78
    lis
    -0.78
    Jr
    -0.77
    uj
    -0.77
    POSITIVE LOGITS
     mitigation
    1.05
     predictive
    1.01
     preservation
    0.97
     retention
    0.97
     optimization
    0.96
     retrieval
    0.96
     consequ
    0.95
     stabilization
    0.94
     visualization
    0.93
     dissemination
    0.93
    Activations Density 0.436%

    No Known Activations