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. 12-RES-JB
    6. 14565
    Prev
    Next
    INDEX
    Explanations

    syntax and keywords related to programming in C++ and OpenGL

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    programming-related keywords and terms associated with C++ and graphics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     millenn
    -1.17
     metic
    -1.13
     pione
    -1.11
     eleph
    -1.04
     occas
    -1.04
    DeliveryDate
    -1.03
    ortunately
    -1.03
    oreAnd
    -1.01
     earthqu
    -1.00
     corrid
    -1.00
    POSITIVE LOGITS
    }}
    1.07
    };
    1.04
    }
    1.01
    }\
    1.00
    }}}
    0.96
    }.
    0.96
    _{
    0.92
    _
    0.90
     };
    0.90
    },
    0.89
    Activations Density 0.139%

    No Known Activations