© 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. 15516
    Prev
    Next
    INDEX
    Explanations

    names and specific terms related to political and social figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities in various contexts

    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
    ;;
    -0.77
    igate
    -0.67
    ;}
    -0.64
    ";
    -0.62
    ORK
    -0.62
    };
    -0.61
    .;
    -0.61
     Accessed
    -0.61
    hart
    -0.60
    estern
    -0.60
    POSITIVE LOGITS
     nonetheless
    1.78
     nevertheless
    1.60
     hasn
    1.23
     persists
    1.20
    etheless
    1.17
     remains
    1.16
     insists
    1.16
     still
    1.15
     doesn
    1.14
     remained
    1.14
    Activations Density 0.694%

    No Known Activations