Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21713
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    mathematical notation and symbols, particularly those involving exponential functions and expressions

    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
     Canal
    -0.87
     Glock
    -0.80
     Hook
    -0.73
     corrid
    -0.71
     Outdoor
    -0.70
     hook
    -0.69
     Mayhem
    -0.68
     hooked
    -0.68
     Leica
    -0.67
     Bowie
    -0.67
    POSITIVE LOGITS
    });
    1.16
    };
    1.05
    },
    1.04
    }}
    1.03
    }{
    1.02
    STAR
    1.01
    }
    0.99
    })
    0.98
    favorite
    0.98
    lambda
    0.96
    Activations Density 0.023%

    No Known Activations