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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    6. 5989
    Prev
    Next
    INDEX
    Explanations

    code snippets within curly braces

    oai_token-act-pair · gpt-3.5-turbo

    json structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hancock
    -0.77
     reeling
    -0.74
     Glock
    -0.72
     recalling
    -0.68
     Outdoor
    -0.66
     Tsarnaev
    -0.65
     outdoors
    -0.65
     Luxem
    -0.65
     recre
    -0.65
     Noon
    -0.64
    POSITIVE LOGITS
    },
    1.33
    };
    1.32
    }}
    1.25
    });
    1.22
    }{
    1.17
    })
    1.17
    }
    1.11
    }}}
    1.11
    }:
    1.00
    flush
    0.98
    Activations Density 0.018%

    No Known Activations