© 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. 6-RES-JB
    11. 1584
    Prev
    Next
    INDEX
    Explanations

    JavaScript function definitions

    oai_token-act-pair · gpt-3.5-turbo

    code structure, particularly instances of opening curly braces and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corrid
    -0.98
    stellar
    -0.82
    vre
    -0.77
    ãĥĥãĥī
    -0.73
    ãĥ´
    -0.73
    hof
    -0.68
    acus
    -0.68
     bunk
    -0.68
     leveled
    -0.67
    姫
    -0.67
    POSITIVE LOGITS
    };
    1.12
     /*
    0.99
     //
    0.97
     Âł Âł Âł Âł
    0.93
    },
    0.91
     }
    0.88
    alert
    0.85
    })
    0.82
    });
    0.81
     Âł Âł
    0.81
    Activations Density 0.015%

    No Known Activations